(all)
Global Humanities | History of Humanities | Liberal Arts | Humanities and Higher Education | Humanities as Research Activity | Humanities Teaching & Curricula | Humanities and the Sciences | Medical Humanities | Public Humanities | Humanities Advocacy | Humanities and Social Groups | Value of Humanities | Humanities and Economic Value | Humanities Funding | Humanities Statistics | Humanities Surveys | "Crisis" of the Humanities
Humanities Organizations: Humanities Councils (U.S.) | Government Agencies | Foundations | Scholarly Associations
Humanities in: Africa | Asia (East) | Asia (South) | Australasia | Europe | Latin America | Middle East | North America: Canada - Mexico - United States | Scandinavia | United Kingdom
(all)
Lists of News Sources | Databases with News Archives | History of Journalism | Journalism Studies | Journalism Statistics | Journalism Organizations | Student Journalism | Data Journalism | Media Frames (analyzing & changing media narratives using "frame theory") | Media Bias | Fake News | Journalism and Minorities | Journalism and Women | Press Freedom | News & Social Media
(all)
Corpus Representativeness
Comparison paradigms for idea of a corpus: Archives as Paradigm | Canons as Paradigm | Editions as Paradigm | Corpus Linguistics as Paradigm
(all)
Artificial Intelligence | Big Data | Data Mining | Data Notebooks (Jupyter Notebooks) | Data Visualization (see also Topic Model Visualizations) | Hierarchical Clustering | Interpretability & Explainability (see also Topic Model Interpretation) | Mapping | Natural Language Processing | Network Analysis | Open Science | Reporting & Documentation Methods | Reproducibility | Sentiment Analysis | Social Media Analysis | Statistical Methods | Text Analysis (see also Topic Modeling) | Text Classification | Wikification | Word Embedding & Vector Semantics
Topic Modeling (all)
Selected DH research and resources bearing on, or utilized by, the WE1S project.
(all)
Distant Reading | Cultural Analytics | | Sociocultural Approaches | Topic Modeling in DH | Non-consumptive Use
Searchable version of bibliography on Zotero site
For WE1S developers: Biblio style guide | Biblio collection form (suggest additions) | WE1S Bibliography Ontology Outline
This bibliography page concentrates on citations for algorithms and software for making topic models. Interface tools for viewing or exploring topic models are cited on the topic model visualization bibliography page. (There is some overlap in categories, however, since topic model interface tools often include embedded uses of topic-model making algorithms such as LDA and application software such as Mallet.)
2133649
Topic Model Algorithm
1
chicago-fullnote-bibliography
50
date
desc
year
1
1
1
2468
https://we1s.ucsb.edu/wp-content/plugins/zotpress/
%7B%22status%22%3A%22success%22%2C%22updateneeded%22%3Afalse%2C%22instance%22%3Afalse%2C%22meta%22%3A%7B%22request_last%22%3A0%2C%22request_next%22%3A0%2C%22used_cache%22%3Atrue%7D%2C%22data%22%3A%5B%7B%22key%22%3A%228ZQTAL8H%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Guille%20and%20Soriano-Morales%22%2C%22parsedDate%22%3A%222016%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EGuille%2C%20Adrien%2C%20and%20Edmundo-Pavel%20Soriano-Morales.%20%26%23x201C%3BTOM%3A%20A%20Library%20for%20Topic%20Modeling%20and%20Browsing.%26%23x201D%3B%20In%20%3Ci%3EConf%26%23xE9%3Brence%20Sur%20l%26%23x2019%3BExtraction%20et%20La%20Gestion%20Des%20Connaissances%3C%5C%2Fi%3E.%20Actes%20de%20La%2016%26%23xE8%3Bme%20Conf%26%23xE9%3Brence%20Sur%20l%26%23x2019%3BExtraction%20et%20La%20Gestion%20Des%20Connaissances.%20Reims%2C%20France%2C%202016.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27https%3A%5C%2F%5C%2Fhal.archives-ouvertes.fr%5C%2Fhal-01442868%27%3Ehttps%3A%5C%2F%5C%2Fhal.archives-ouvertes.fr%5C%2Fhal-01442868%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3D8ZQTAL8H%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22TOM%3A%20A%20library%20for%20topic%20modeling%20and%20browsing%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrien%22%2C%22lastName%22%3A%22Guille%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Edmundo-Pavel%22%2C%22lastName%22%3A%22Soriano-Morales%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20presents%20TOM%20%28TOpic%20Modeling%29%2C%20a%20Python%20library%20for%20topic%20modeling%20and%20browsing.%20Its%20objective%20is%20to%20allow%20for%20an%20efficient%20analysis%20of%20a%20text%20corpus%20from%20start%20to%20finish%2C%20via%20the%20discovery%20of%20latent%20topics.%20To%20this%20end%2C%20TOM%20features%20advanced%20functions%20for%20preparing%20and%20vectorizing%20a%20text%20corpus.%20It%20also%20offers%20a%20unified%20interface%20for%20two%20topic%20models%20%28namely%20LDA%20using%20either%20variational%20inference%20or%20Gibbs%20sampling%2C%20and%20NMF%20using%20alternating%20least-square%20with%20a%20projected%20gradient%20method%29%2C%20and%20implements%20three%20state-of-the-art%20methods%20for%20estimating%20the%20optimal%20number%20of%20topics%20to%20model%20a%20corpus.%22%2C%22date%22%3A%222016%22%2C%22proceedingsTitle%22%3A%22Conf%5Cu00e9rence%20sur%20l%27Extraction%20et%20la%20Gestion%20des%20Connaissances%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fhal.archives-ouvertes.fr%5C%2Fhal-01442868%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A46%3A50Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20visualization%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22MHDFCTF5%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Vuli%5Cu0107%20et%20al.%22%2C%22parsedDate%22%3A%222015%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EVuli%26%23x107%3B%2C%20Ivan%2C%20Wim%20De%20Smet%2C%20Jie%20Tang%2C%20and%20Marie-Francine%20Moens.%20%26%23x201C%3BProbabilistic%20Topic%20Modeling%20in%20Multilingual%20Settings%3A%20An%20Overview%20of%20Its%20Methodology%20and%20Applications.%26%23x201D%3B%20%3Ci%3EInformation%20Processing%20%26amp%3B%20Management%3C%5C%2Fi%3E%2051%2C%20no.%201%20%282015%29%3A%20111%26%23x2013%3B47.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27http%3A%5C%2F%5C%2Fkeg.cs.tsinghua.edu.cn%5C%2Fjietang%5C%2Fpublications%5C%2Fipm15-xLiTe-IvanVulic-overview-topic-model-multilingual.pdf%27%3Ehttp%3A%5C%2F%5C%2Fkeg.cs.tsinghua.edu.cn%5C%2Fjietang%5C%2Fpublications%5C%2Fipm15-xLiTe-IvanVulic-overview-topic-model-multilingual.pdf%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DMHDFCTF5%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Probabilistic%20topic%20modeling%20in%20multilingual%20settings%3A%20An%20overview%20of%20its%20methodology%20and%20applications%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ivan%22%2C%22lastName%22%3A%22Vuli%5Cu0107%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wim%22%2C%22lastName%22%3A%22De%20Smet%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jie%22%2C%22lastName%22%3A%22Tang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Marie-Francine%22%2C%22lastName%22%3A%22Moens%22%7D%5D%2C%22abstractNote%22%3A%22Probabilistic%20topic%20models%20are%20unsupervised%20generative%20models%20which%20model%20document%20content%20as%20a%20two-step%20generation%20process%2C%20that%20is%2C%20documents%20are%20observed%20as%20mixtures%20of%20latent%20concepts%20or%20topics%2C%20while%20topics%20are%20probability%20distributions%20over%20vocabulary%20words.%20Recently%2C%20a%20significant%20research%20effort%20has%20been%20invested%20into%20transferring%20the%20probabilistic%20topic%20modeling%20concept%20from%20monolingual%20to%20multilingual%20settings.%20Novel%20topic%20models%20have%20been%20designed%20to%20work%20with%20parallel%20and%20comparable%20texts.%20We%20define%20multilingual%20probabilistic%20topic%20modeling%20%28MuPTM%29%20and%20present%20the%20first%20full%20overview%20of%20the%20current%20research%2C%20methodology%2C%20advantages%20and%20limitations%20in%20MuPTM.%20As%20a%20representative%20example%2C%20we%20choose%20a%20natural%20extension%20of%20the%20omnipresent%20LDA%20model%20to%20multilingual%20settings%20called%20bilingual%20LDA%20%28BiLDA%29.%20We%20provide%20a%20thorough%20overview%20of%20this%20representative%20multilingual%20model%20from%20its%20high-level%20modeling%20assumptions%20down%20to%20its%20mathematical%20foundations.%20We%20demonstrate%20how%20to%20use%20the%20data%20representation%20by%20means%20of%20output%20sets%20of%20%28i%29%20per-topic%20word%20distributions%20and%20%28ii%29%20per-document%20topic%20distributions%20coming%20from%20a%20multilingual%20probabilistic%20topic%20model%20in%20various%20real-life%20cross-lingual%20tasks%20involving%20different%20languages%2C%20without%20any%20external%20language%20pair%20dependent%20translation%20resource%3A%20%281%29%20cross-lingual%20event-centered%20news%20clustering%2C%20%282%29%20cross-lingual%20document%20classification%2C%20%283%29%20cross-lingual%20semantic%20similarity%2C%20and%20%284%29%20cross-lingual%20information%20retrieval.%20We%20also%20briefly%20review%20several%20other%20applications%20present%20in%20the%20relevant%20literature%2C%20and%20introduce%20and%20illustrate%20two%20related%20modeling%20concepts%3A%20topic%20smoothing%20and%20topic%20pruning.%20In%20summary%2C%20this%20article%20encompasses%20the%20current%20research%20in%20multilingual%20probabilistic%20topic%20modeling.%20By%20presenting%20a%20series%20of%20potential%20applications%2C%20we%20reveal%20the%20importance%20of%20the%20language-independent%20and%20language%20pair%20independent%20data%20representations%20by%20means%20of%20MuPTM.%20We%20provide%20clear%20directions%20for%20future%20research%20in%20the%20field%20by%20providing%20a%20systematic%20overview%20of%20how%20to%20link%20and%20transfer%20aspect%20knowledge%20across%20corpora%20written%20in%20different%20languages%20via%20the%20shared%20space%20of%20latent%20cross-lingual%20topics%2C%20that%20is%2C%20how%20to%20effectively%20employ%20learned%20per-topic%20word%20distributions%20and%20per-document%20topic%20distributions%20of%20any%20multilingual%20probabilistic%20topic%20model%20in%20various%20cross-lingual%20applications%22%2C%22date%22%3A%222015%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fkeg.cs.tsinghua.edu.cn%5C%2Fjietang%5C%2Fpublications%5C%2Fipm15-xLiTe-IvanVulic-overview-topic-model-multilingual.pdf%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A44%3A53Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20multilingual%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%227RW8NZVN%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Blei%22%2C%22parsedDate%22%3A%222012%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EBlei%2C%20David%20M.%20%26%23x201C%3BProbabilistic%20Topic%20Models.%26%23x201D%3B%20%3Ci%3ECommunications%20of%20the%20ACM%3C%5C%2Fi%3E%2055%2C%20no.%204%20%282012%29%3A%2077%26%23x2013%3B84.%20%3Ca%20class%3D%27zp-DOIURL%27%20href%3D%27https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F2133806.2133826%27%3Ehttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F2133806.2133826%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3D7RW8NZVN%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Probabilistic%20topic%20models%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%20M.%22%2C%22lastName%22%3A%22Blei%22%7D%5D%2C%22abstractNote%22%3A%22This%20article%20encompasses%20the%20current%20research%20in%20multilingual%20probabilistic%20topic%20modeling.%20By%20presenting%20a%20series%20of%20potential%20applications%2C%20the%20article%20reveals%20the%20importance%20of%20the%20language-independent%20and%20language%20pair%20independent%20data%20representations%20by%20means%20of%20MuPTM.%20The%20article%20provides%20clear%20directions%20for%20future%20research%20in%20the%20field%20by%20providing%20a%20systematic%20overview%20of%20how%20to%20link%20and%20transfer%20aspect%20knowledge%20across%20corpora%20written%20in%20different%20languages%20via%20the%20shared%20space%20of%20latent%20cross-lingual%20topics.%22%2C%22date%22%3A%222012%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1145%5C%2F2133806.2133826%22%2C%22ISSN%22%3A%2200010782%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fdoi%5C%2F10.1145%5C%2F2133806.2133826%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222024-02-08T08%3A25%3A45Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20introductions%20and%20tutorials%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22J7U9JJV8%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Arora%20et%20al.%22%2C%22parsedDate%22%3A%222012%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EArora%2C%20Sanjeev%2C%20Rong%20Ge%2C%20Yoni%20Halpern%2C%20David%20Mimno%2C%20Ankur%20Moitra%2C%20David%20Sontag%2C%20Yichen%20Wu%2C%20and%20Michael%20Zhu.%20%26%23x201C%3BA%20Practical%20Algorithm%20for%20Topic%20Modeling%20with%20Provable%20Guarantees.%26%23x201D%3B%20%3Ci%3EArXiv%3A1212.4777%20%5BCs%2C%20Stat%5D%3C%5C%2Fi%3E%2C%202012.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F1212.4777%27%3Ehttp%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F1212.4777%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DJ7U9JJV8%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22A%20Practical%20Algorithm%20for%20Topic%20Modeling%20with%20Provable%20Guarantees%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sanjeev%22%2C%22lastName%22%3A%22Arora%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Rong%22%2C%22lastName%22%3A%22Ge%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yoni%22%2C%22lastName%22%3A%22Halpern%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Mimno%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ankur%22%2C%22lastName%22%3A%22Moitra%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Sontag%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yichen%22%2C%22lastName%22%3A%22Wu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michael%22%2C%22lastName%22%3A%22Zhu%22%7D%5D%2C%22abstractNote%22%3A%22Most%20approaches%20to%20topic%20model%20inference%20have%20been%20based%20on%20a%20maximum%20likelihood%20objective.%20Efficient%20algorithms%20exist%20that%20approximate%20this%20objective%2C%20but%20they%20have%20no%20provable%20guarantees.%20Recently%2C%20algorithms%20have%20been%20introduced%20that%20provide%20provable%20bounds%2C%20but%20these%20algorithms%20are%20not%20practical%20because%20they%20are%20inefficient%20and%20not%20robust%20to%20violations%20of%20model%20assumptions.%20This%20paper%20presents%20an%20algorithm%20for%20topic%20model%20inference%20that%20is%20both%20provable%20and%20practical.%20The%20algorithm%20produces%20results%20comparable%20to%20the%20best%20MCMC%20implementations%20while%20running%20orders%20of%20magnitude%20faster.%22%2C%22date%22%3A%222012%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F1212.4777%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A26%3A06Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22SHMGE7FS%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Wang%20et%20al.%22%2C%22parsedDate%22%3A%222012%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EWang%2C%20Chong%2C%20David%20Blei%2C%20and%20David%20Heckerman.%20%26%23x201C%3BContinuous%20Time%20Dynamic%20Topic%20Models.%26%23x201D%3B%20%3Ci%3EArXiv%3A1206.3298%20%5BCs%2C%20Stat%5D%3C%5C%2Fi%3E%2C%202012.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F1206.3298%27%3Ehttp%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F1206.3298%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DSHMGE7FS%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Continuous%20Time%20Dynamic%20Topic%20Models%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chong%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Blei%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Heckerman%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20develops%20the%20continuous%20time%20dynamic%20topic%20model%20%28cDTM%29.%20The%20cDTM%20is%20a%20dynamic%20topic%20model%20that%20uses%20Brownian%20motion%20to%20model%20the%20latent%20topics%20through%20a%20sequential%20collection%20of%20documents%2C%20where%20a%20%5C%22topic%5C%22%20is%20a%20pattern%20of%20word%20use%20that%20we%20expect%20to%20evolve%20over%20the%20course%20of%20the%20collection.%20This%20paper%20derives%20an%20efficient%20variational%20approximate%20inference%20algorithm%20that%20takes%20advantage%20of%20the%20sparsity%20of%20observations%20in%20text%2C%20a%20property%20that%20lets%20us%20easily%20handle%20many%20time%20points.%22%2C%22date%22%3A%222012%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F1206.3298%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A33%3A48Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20longitudinal%20over%20time%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22BIYCRE63%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Wu%20et%20al.%22%2C%22parsedDate%22%3A%222012%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EWu%2C%20Hao%2C%20Jiajun%20Bu%2C%20Chun%20Chen%2C%20Jianke%20Zhu%2C%20Lijun%20Zhang%2C%20Haifeng%20Liu%2C%20Can%20Wang%2C%20and%20Deng%20Cai.%20%26%23x201C%3BLocally%20Discriminative%20Topic%20Modeling.%26%23x201D%3B%20%3Ci%3EPattern%20Recognition%3C%5C%2Fi%3E%2045%2C%20no.%201%20%282012%29%3A%20617%26%23x2013%3B25.%20%3Ca%20class%3D%27zp-DOIURL%27%20href%3D%27https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.patcog.2011.04.029%27%3Ehttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1016%5C%2Fj.patcog.2011.04.029%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DBIYCRE63%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Locally%20discriminative%20topic%20modeling%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hao%22%2C%22lastName%22%3A%22Wu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jiajun%22%2C%22lastName%22%3A%22Bu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chun%22%2C%22lastName%22%3A%22Chen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jianke%22%2C%22lastName%22%3A%22Zhu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lijun%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Haifeng%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Can%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Deng%22%2C%22lastName%22%3A%22Cai%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20proposes%20locally%20discriminative%20topic%20model%20%28LDTM%29%2C%20a%20novel%20topic%20modeling%20approach%20which%20considers%20both%20generative%20and%20discriminative%20structures%20of%20the%20data%20space.%20Different%20from%20PLSA%20and%20LDA%20in%20which%20the%20topic%20distribution%20of%20a%20document%20is%20dependent%20on%20all%20the%20other%20documents%2C%20LDTM%20takes%20a%20local%20perspective%20that%20the%20topic%20distribution%20of%20each%20document%20is%20strongly%20dependent%20on%20its%20neighbors.%20By%20modeling%20the%20local%20relationships%20of%20documents%20within%20each%20neighborhood%20via%20a%20local%20linear%20model%2C%20we%20learn%20topic%20distributions%20that%20vary%20smoothly%20along%20the%20geodesics%20of%20the%20data%20manifold%2C%20and%20can%20better%20capture%20the%20discriminative%20structure%20in%20the%20data.%20The%20experimental%20results%20on%20text%20clustering%20and%20web%20page%20categorization%20demonstrate%20the%20effectiveness%20of%20our%20proposed%20approach.%22%2C%22date%22%3A%222012%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1016%5C%2Fj.patcog.2011.04.029%22%2C%22ISSN%22%3A%220031-3203%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fwww.sciencedirect.com%5C%2Fscience%5C%2Farticle%5C%2Fpii%5C%2FS0031320311001889%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222020-07-01T20%3A52%3A31Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22PKJHFGG8%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Ponweiser%22%2C%22parsedDate%22%3A%222012%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EPonweiser%2C%20Martin.%20%26%23x201C%3BLatent%20Dirichlet%20Allocation%20in%20R.%26%23x201D%3B%20Diploma%20Thesis%2C%20Vienna%20University%20of%20Economics%20and%20Business%2C%202012.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27http%3A%5C%2F%5C%2Fepub.wu.ac.at%5C%2F3558%5C%2F%27%3Ehttp%3A%5C%2F%5C%2Fepub.wu.ac.at%5C%2F3558%5C%2F%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DPKJHFGG8%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22thesis%22%2C%22title%22%3A%22Latent%20Dirichlet%20Allocation%20in%20R%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Martin%22%2C%22lastName%22%3A%22Ponweiser%22%7D%5D%2C%22abstractNote%22%3A%22This%20thesis%20focuses%20on%20LDA%27s%20practical%20application.%20Its%20main%20goal%20is%20the%20replication%20of%20the%20data%20analyses%20from%20the%202004%20LDA%20paper%20%5Cu201cFinding%20scientific%20topics%5Cu201d%20by%20Thomas%20Griffiths%20and%20Mark%20Steyvers%20within%20the%20framework%20of%20the%20R%20statistical%20programming%20language%20and%20the%20R%5C%5Ctextasciitildepackage%20topic%20models%20by%20Bettina%20Gr%5Cu00c3%5Cu00bcn%20and%20Kurt%20Hornik.%20The%20complete%20process%2C%20including%20extraction%20of%20a%20text%20corpus%20from%20the%20PNAS%20journal%27s%20website%2C%20data%20preprocessing%2C%20transformation%20into%20a%20document-term%20matrix%2C%20model%20selection%2C%20model%20estimation%2C%20as%20well%20as%20presentation%20of%20the%20results%2C%20is%20fully%20documented%20and%20commented.%20The%20outcome%20closely%20matches%20the%20analyses%20of%20the%20original%20paper%2C%20therefore%20the%20research%20by%20Griffiths%5C%2FSteyvers%20can%20be%20reproduced.%20Furthermore%2C%20this%20thesis%20proves%20the%20suitability%20of%20the%20R%20environment%20for%20text%20mining%20with%20LDA.%22%2C%22thesisType%22%3A%22Diploma%20Thesis%22%2C%22university%22%3A%22Vienna%20University%20of%20Economics%20and%20Business%22%2C%22date%22%3A%222012%22%2C%22language%22%3A%22en%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fepub.wu.ac.at%5C%2F3558%5C%2F%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A43%3A13Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20optimization%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22H6QJSRSF%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Boyd-Graber%20and%20Resnik%22%2C%22parsedDate%22%3A%222010%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EBoyd-Graber%2C%20Jordan%2C%20and%20Philip%20Resnik.%20%26%23x201C%3BHolistic%20Sentiment%20Analysis%20across%20Languages%3A%20Multilingual%20Supervised%20Latent%20Dirichlet%20Allocation.%26%23x201D%3B%20In%20%3Ci%3EProceedings%20of%20the%202010%20Conference%20on%20Empirical%20Methods%20in%20Natural%20Language%20Processing%3C%5C%2Fi%3E%2C%2045%26%23x2013%3B55.%20Association%20for%20Computational%20Linguistics%2C%202010.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27http%3A%5C%2F%5C%2Fwww.aclweb.org%5C%2Fanthology%5C%2FD10-1005%27%3Ehttp%3A%5C%2F%5C%2Fwww.aclweb.org%5C%2Fanthology%5C%2FD10-1005%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DH6QJSRSF%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Holistic%20sentiment%20analysis%20across%20languages%3A%20Multilingual%20supervised%20latent%20Dirichlet%20allocation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jordan%22%2C%22lastName%22%3A%22Boyd-Graber%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Philip%22%2C%22lastName%22%3A%22Resnik%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20develops%20multilingual%20supervised%20latent%20Dirichlet%20allocation%20%28MlSLDA%29%2C%20a%20probabilistic%20generative%20model%20that%20allows%20insights%20gleaned%20from%20one%20language%27s%20data%20to%20inform%20how%20the%20model%20captures%20properties%20of%20other%20languages.%20This%20work%20shows%20MlSLDA%20can%20build%20topics%20that%20are%20consistent%20across%20languages%2C%20discover%20sensible%20bilingual%20lexical%20correspondences%2C%20and%20leverage%20multilingual%20corpora%20to%20better%20predict%20sentiment.%22%2C%22date%22%3A%222010%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%202010%20Conference%20on%20Empirical%20Methods%20in%20Natural%20Language%20Processing%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fwww.aclweb.org%5C%2Fanthology%5C%2FD10-1005%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A33%3A38Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Natural%20language%20processing%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20multilingual%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%224TH5QB4X%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Saria%20et%20al.%22%2C%22parsedDate%22%3A%222010%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3ESaria%2C%20Suchi%2C%20Daphne%20Koller%2C%20and%20Anna%20Penn.%20%26%23x201C%3BDiscovering%20Shared%20and%20Individual%20Latent%20Structure%20in%20Multiple%20Time%20Series.%26%23x201D%3B%20%3Ci%3EArXiv%3A1008.2028%20%5BCs%2C%20Stat%5D%3C%5C%2Fi%3E%2C%202010.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F1008.2028%27%3Ehttp%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F1008.2028%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3D4TH5QB4X%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Discovering%20shared%20and%20individual%20latent%20structure%20in%20multiple%20time%20series%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suchi%22%2C%22lastName%22%3A%22Saria%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daphne%22%2C%22lastName%22%3A%22Koller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anna%22%2C%22lastName%22%3A%22Penn%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20proposes%20a%20nonparametric%20Bayesian%20method%20for%20exploratory%20data%20analysis%20and%20feature%20construction%20in%20continuous%20time%20series.%20Our%20method%20focuses%20on%20understanding%20shared%20features%20in%20a%20set%20of%20time%20series%20that%20exhibit%20significant%20individual%20variability.%20Our%20method%20builds%20on%20the%20framework%20of%20latent%20Diricihlet%20allocation%20%28LDA%29%20and%20its%20extension%20to%20hierarchical%20Dirichlet%20processes%2C%20which%20allows%20us%20to%20characterize%20each%20series%20as%20switching%20between%20latent%20%5Cu201ctopics%5Cu201d%2C%20where%20each%20topic%20is%20characterized%20as%20a%20distribution%20over%20%5Cu201cwords%5Cu201d%20that%20specify%20the%20series%20dynamics.%20However%2C%20unlike%20standard%20applications%20of%20LDA%2C%20we%20discover%20the%20words%20as%20we%20learn%20the%20model.%20We%20apply%20this%20model%20to%20the%20task%20of%20tracking%20the%20physiological%20signals%20of%20premature%20infants%3B%20our%20model%20obtains%20clinically%20significant%20insights%20as%20well%20as%20useful%20features%20for%20supervised%20learning%20tasks.%22%2C%22date%22%3A%222010%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F1008.2028%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A33%3A48Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20longitudinal%20over%20time%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22VIT76NVP%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Andrews%20and%20Vigliocco%22%2C%22parsedDate%22%3A%222010%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EAndrews%2C%20Mark%2C%20and%20Gabriella%20Vigliocco.%20%26%23x201C%3BThe%20Hidden%20Markov%20Topic%20Model%3A%20A%20Probabilistic%20Model%20of%20Semantic%20Representation.%26%23x201D%3B%20%3Ci%3ETopics%20in%20Cognitive%20Science%3C%5C%2Fi%3E%202%2C%20no.%201%20%282010%29%3A%20101%26%23x2013%3B13.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27https%3A%5C%2F%5C%2Fonlinelibrary.wiley.com%5C%2Fdoi%5C%2Fpdf%5C%2F10.1111%5C%2Fj.1756-8765.2009.01074.x%27%3Ehttps%3A%5C%2F%5C%2Fonlinelibrary.wiley.com%5C%2Fdoi%5C%2Fpdf%5C%2F10.1111%5C%2Fj.1756-8765.2009.01074.x%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DVIT76NVP%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22The%20hidden%20Markov%20topic%20model%3A%20A%20probabilistic%20model%20of%20semantic%20representation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mark%22%2C%22lastName%22%3A%22Andrews%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gabriella%22%2C%22lastName%22%3A%22Vigliocco%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20describes%20a%20model%20that%20learns%20semantic%20representations%20from%20the%20distributional%20statistics%20of%20language.%20This%20model%2C%20however%2C%20goes%20beyond%20the%20common%20bag-of-words%20paradigm%2C%20and%20infers%20semantic%20representations%20by%20taking%20into%20account%20the%20inherent%20sequential%20nature%20of%20linguistic%20data.%20The%20described%20model%2C%20Hidden%20Markov%20Topics%20model%2C%20is%20a%20natural%20extension%20of%20the%20current%20state%20of%20the%20art%20in%20Bayesian%20bag-of-words%20models%2C%20that%20is%2C%20the%20Topics%20model%20of%20Griffiths%2C%20Steyvers%2C%20and%20Tenenbaum%20%282007%29%2C%20preserving%20its%20strengths%20while%20extending%20its%20scope%20to%20incorporate%20more%20fine-grained%20linguistic%20information%22%2C%22date%22%3A%222010%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fonlinelibrary.wiley.com%5C%2Fdoi%5C%2Fpdf%5C%2F10.1111%5C%2Fj.1756-8765.2009.01074.x%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A46%3A13Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22K3R387B9%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Wallach%20et%20al.%22%2C%22parsedDate%22%3A%222009%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EWallach%2C%20Hanna%20M.%2C%20David%20Mimno%2C%20and%20Andrew%20McCallum.%20%26%23x201C%3BRethinking%20LDA%3A%20Why%20Priors%20Matter.%26%23x201D%3B%20In%20%3Ci%3EProceedings%20of%20the%2022Nd%20International%20Conference%20on%20Neural%20Information%20Processing%20Systems%3C%5C%2Fi%3E%2C%201973%26%23x2013%3B81.%20NIPS%26%23x2019%3B09.%20USA%3A%20Curran%20Associates%20Inc.%2C%202009.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27http%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fcitation.cfm%3Fid%3D2984093.2984314%27%3Ehttp%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fcitation.cfm%3Fid%3D2984093.2984314%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DK3R387B9%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Rethinking%20LDA%3A%20Why%20Priors%20Matter%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hanna%20M.%22%2C%22lastName%22%3A%22Wallach%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Mimno%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrew%22%2C%22lastName%22%3A%22McCallum%22%7D%5D%2C%22abstractNote%22%3A%22Implementations%20of%20topic%20models%20typically%20use%20symmetric%20Dirichlet%20priors%20with%20fixed%20concentration%20parameters%2C%20with%20the%20implicit%20assumption%20that%20such%20%5C%22smoothing%20parameters%5C%22%20have%20little%20practical%20effect.%20This%20paper%20explores%20several%20classes%20of%20structured%20priors%20for%20topic%20models.%22%2C%22date%22%3A%222009%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%2022Nd%20International%20Conference%20on%20Neural%20Information%20Processing%20Systems%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22978-1-61567-911-9%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fcitation.cfm%3Fid%3D2984093.2984314%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A40%3A56Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22R28H6FVC%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Ramage%20et%20al.%22%2C%22parsedDate%22%3A%222009%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3ERamage%2C%20Daniel%2C%20David%20Hall%2C%20Ramesh%20Nallapati%2C%20and%20Christopher%20D.%20Manning.%20%26%23x201C%3BLabeled%20LDA%3A%20A%20Supervised%20Topic%20Model%20for%20Credit%20Attribution%20in%20Multi-Labeled%20Corpora.%26%23x201D%3B%20In%20%3Ci%3EProceedings%20of%20the%202009%20Conference%20on%20Empirical%20Methods%20in%20Natural%20Language%20Processing%3A%20Volume%201%20-%20Volume%201%3C%5C%2Fi%3E%2C%20248%26%23x2013%3B56.%20EMNLP%20%26%23x2019%3B09.%20Stroudsburg%2C%20PA%2C%20USA%3A%20Association%20for%20Computational%20Linguistics%2C%202009.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27http%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fcitation.cfm%3Fid%3D1699510.1699543%27%3Ehttp%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fcitation.cfm%3Fid%3D1699510.1699543%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DR28H6FVC%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Labeled%20LDA%3A%20A%20Supervised%20Topic%20Model%20for%20Credit%20Attribution%20in%20Multi-labeled%20Corpora%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Ramage%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Hall%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ramesh%22%2C%22lastName%22%3A%22Nallapati%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Christopher%20D.%22%2C%22lastName%22%3A%22Manning%22%7D%5D%2C%22abstractNote%22%3A%22A%20significant%20portion%20of%20the%20world%27s%20text%20is%20tagged%20by%20readers%20on%20social%20bookmarking%20websites.%20Credit%20attribution%20is%20an%20inherent%20problem%20in%20these%20corpora%20because%20most%20pages%20have%20multiple%20tags%2C%20but%20the%20tags%20do%20not%20always%20apply%20with%20equal%20specificity%20across%20the%20whole%20document.%20Solving%20the%20credit%20attribution%20problem%20requires%20associating%20each%20word%20in%20a%20document%20with%20the%20most%20appropriate%20tags%20and%20vice%20versa.%20This%20paper%20introduces%20Labeled%20LDA%2C%20a%20topic%20model%20that%20constrains%20Latent%20Dirichlet%20Allocation%20by%20defining%20a%20one-to-one%20correspondence%20between%20LDA%27s%20latent%20topics%20and%20user%20tags.%20This%20allows%20Labeled%20LDA%20to%20directly%20learn%20word-tag%20correspondences.%20The%20authors%20demonstrate%20Labeled%20LDA%27s%20improved%20expressiveness%20over%20traditional%20LDA%20with%20visualizations%20of%20a%20corpus%20of%20tagged%20web%20pages%20from%20del.icio.us.%22%2C%22date%22%3A%222009%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%202009%20Conference%20on%20Empirical%20Methods%20in%20Natural%20Language%20Processing%3A%20Volume%201%20-%20Volume%201%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22978-1-932432-59-6%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fcitation.cfm%3Fid%3D1699510.1699543%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A42%3A58Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20applied%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20labeling%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22MMXU69R7%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Boyd-Graber%20and%20Blei%22%2C%22parsedDate%22%3A%222009%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EBoyd-Graber%2C%20Jordan%2C%20and%20David%20M.%20Blei.%20%26%23x201C%3BMultilingual%20Topic%20Models%20for%20Unaligned%20Text.%26%23x201D%3B%20In%20%3Ci%3EProceedings%20of%20the%20Twenty-Fifth%20Conference%20on%20Uncertainty%20in%20Artificial%20Intelligence%3C%5C%2Fi%3E%2C%2075%26%23x2013%3B82.%20AUAI%20Press%2C%202009.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27https%3A%5C%2F%5C%2Farxiv.org%5C%2Fpdf%5C%2F1205.2657%27%3Ehttps%3A%5C%2F%5C%2Farxiv.org%5C%2Fpdf%5C%2F1205.2657%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DMMXU69R7%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Multilingual%20topic%20models%20for%20unaligned%20text%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jordan%22%2C%22lastName%22%3A%22Boyd-Graber%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%20M.%22%2C%22lastName%22%3A%22Blei%22%7D%5D%2C%22abstractNote%22%3A%22The%20multilingual%20topic%20model%20for%20unaligned%20text%20%28MuTo%29%20is%20a%20probabilistic%20model%20of%20text%20that%20is%20designed%20to%20analyze%20corpora%20composed%20of%20documents%20in%20two%20languages.%20From%20these%20documents%2C%20MuTo%20uses%20stochastic%20EM%20to%20simultaneously%20discover%20both%20a%20matching%20between%20the%20languages%20and%20multilingual%20latent%20topics.%20This%20study%20demonstrates%20that%20MuTo%20is%20able%20to%20find%20shared%20topics%20on%20real-world%20multilingual%20corpora%2C%20successfully%20pairing%20related%20documents%20across%20languages.%20MuTo%20provides%20a%20new%20framework%20for%20creating%20multilingual%20topic%20models%20without%20needing%20carefully%20curated%20parallel%20corpora%20and%20allows%20applications%20built%20using%20the%20topic%20model%20formalism%20to%20be%22%2C%22date%22%3A%222009%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%20Twenty-Fifth%20Conference%20on%20Uncertainty%20in%20Artificial%20Intelligence%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Farxiv.org%5C%2Fpdf%5C%2F1205.2657%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A44%3A05Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20multilingual%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22KAQ9KIP6%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Boyd-Graber%20and%20Blei%22%2C%22parsedDate%22%3A%222009%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EBoyd-Graber%2C%20Jordan%20L.%2C%20and%20David%20M.%20Blei.%20%26%23x201C%3BSyntactic%20Topic%20Models.%26%23x201D%3B%20In%20%3Ci%3EAdvances%20in%20Neural%20Information%20Processing%20Systems%3C%5C%2Fi%3E%2C%20185%26%23x2013%3B92%2C%202009.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27https%3A%5C%2F%5C%2Fpapers.nips.cc%5C%2Fpaper%5C%2F3398-syntactic-topic-models.pdf%27%3Ehttps%3A%5C%2F%5C%2Fpapers.nips.cc%5C%2Fpaper%5C%2F3398-syntactic-topic-models.pdf%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DKAQ9KIP6%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Syntactic%20topic%20models%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jordan%20L.%22%2C%22lastName%22%3A%22Boyd-Graber%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%20M.%22%2C%22lastName%22%3A%22Blei%22%7D%5D%2C%22abstractNote%22%3A%22The%20STM%20models%20dependency%20parsed%20corpora%20where%20sentences%20are%20grouped%20into%20documents.%20It%20assumes%20that%20each%20word%20is%20drawn%20from%20a%20latent%20topic%20chosen%20by%20combining%20document-level%20features%20and%20the%20local%20syntactic%20context.%20Each%20document%20has%20a%20distribution%20over%20latent%20topics%2C%20as%20in%20topic%20models%2C%20which%20provides%20the%20semantic%20consistency.%20Each%20element%20in%20the%20dependency%20parse%20tree%20also%20has%20a%20distribution%20over%20the%20topics%20of%20its%20children%2C%20as%20in%20latent-state%20syntax%20models%2C%20which%20provides%20the%20syntactic%20consistency.%20These%20distributions%20are%20convolved%20so%20that%20the%20topic%20of%20each%20word%20is%20likely%20under%20both%20its%20document%20and%20syntactic%20context.%22%2C%22date%22%3A%222009%22%2C%22proceedingsTitle%22%3A%22Advances%20in%20neural%20information%20processing%20systems%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fpapers.nips.cc%5C%2Fpaper%5C%2F3398-syntactic-topic-models.pdf%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A45%3A42Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%229W974FXT%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Boyd-Graber%20et%20al.%22%2C%22parsedDate%22%3A%222007%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EBoyd-Graber%2C%20Jordan%2C%20David%20Blei%2C%20and%20Xiaojin%20Zhu.%20%26%23x201C%3BA%20Topic%20Model%20for%20Word%20Sense%20Disambiguation.%26%23x201D%3B%20In%20%3Ci%3EProceedings%20of%20the%202007%20Joint%20Conference%20on%20Empirical%20Methods%20in%20Natural%20Language%20Processing%20and%20Computational%20Natural%20Language%20Learning%3C%5C%2Fi%3E%2C%201024%26%23x2013%3B33%2C%202007.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27http%3A%5C%2F%5C%2Fwww.aclweb.org%5C%2Fanthology%5C%2FD07-1109%27%3Ehttp%3A%5C%2F%5C%2Fwww.aclweb.org%5C%2Fanthology%5C%2FD07-1109%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3D9W974FXT%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22A%20Topic%20Model%20for%20Word%20Sense%20Disambiguation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jordan%22%2C%22lastName%22%3A%22Boyd-Graber%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22David%22%2C%22lastName%22%3A%22Blei%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaojin%22%2C%22lastName%22%3A%22Zhu%22%7D%5D%2C%22abstractNote%22%3A%22This%20study%20develops%20latent%20Dirichlet%20allocation%20with%20WORDNET%20%28LDAWN%29%2C%20an%20unsupervised%20probabilistic%20topic%20model%20that%20includes%20word%20sense%20as%20a%20hidden%20variable.%20A%20probabilistic%20posterior%20inference%20algorithm%20for%20simultaneously%20disambiguating%20a%20corpus%20and%20learning%20the%20domains%20in%20which%20to%20consider%20each%20word.%20Using%20the%20WORDNET%20hierarchy%20to%20embed%20the%20construction%20of%20Abney%20and%20Light%20%281999%29%20in%20the%20topic%20model%20and%20show%20that%20automatically%20learned%20domains%20improve%20WSD%20accuracy%20compared%20to%20alternative%20contexts.%22%2C%22date%22%3A%222007%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%202007%20Joint%20Conference%20on%20Empirical%20Methods%20in%20Natural%20Language%20Processing%20and%20Computational%20Natural%20Language%20Learning%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fwww.aclweb.org%5C%2Fanthology%5C%2FD07-1109%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A26%3A08Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%225F6TMSKY%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Rosen-Zvi%20et%20al.%22%2C%22parsedDate%22%3A%222007%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3ERosen-Zvi%2C%20Michal%2C%20Yair%20Weiss%2C%20and%20Amit%20Gruber.%20%26%23x201C%3BHidden%20Topic%20Markov%20Models.%26%23x201D%3B%20In%20%3Ci%3EArtificial%20Intelligence%20and%20Statistics%3C%5C%2Fi%3E%2C%20163%26%23x2013%3B70%2C%202007.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27http%3A%5C%2F%5C%2Fproceedings.mlr.press%5C%2Fv2%5C%2Fgruber07a.html%27%3Ehttp%3A%5C%2F%5C%2Fproceedings.mlr.press%5C%2Fv2%5C%2Fgruber07a.html%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3D5F6TMSKY%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Hidden%20Topic%20Markov%20Models%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Michal%22%2C%22lastName%22%3A%22Rosen-Zvi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yair%22%2C%22lastName%22%3A%22Weiss%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Amit%22%2C%22lastName%22%3A%22Gruber%22%7D%5D%2C%22abstractNote%22%3A%22Algorithms%20such%20as%20Latent%20Dirichlet%20Allocation%20%28LDA%29%20have%20achieved%20significant%20progress%20in%20modeling%20word%20document%20relationships.%20These%20algorithms%20assume%20each%20word%20in%20the%20document%20was%20generated%20by%20a...%22%2C%22date%22%3A%222007%22%2C%22proceedingsTitle%22%3A%22Artificial%20Intelligence%20and%20Statistics%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fproceedings.mlr.press%5C%2Fv2%5C%2Fgruber07a.html%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A33%3A47Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%223Y2LX8WJ%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Wang%20et%20al.%22%2C%22parsedDate%22%3A%222007%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EWang%2C%20Chong%2C%20Jinggang%20Wang%2C%20Xing%20Xie%2C%20and%20Wei-Ying%20Ma.%20%26%23x201C%3BMining%20Geographic%20Knowledge%20Using%20Location%20Aware%20Topic%20Model.%26%23x201D%3B%20In%20%3Ci%3EProceedings%20of%20the%204th%20ACM%20Workshop%20on%20Geographical%20Information%20Retrieval%3C%5C%2Fi%3E%2C%2065%26%23x2013%3B70.%20GIR%20%26%23x2019%3B07.%20New%20York%2C%20NY%2C%20USA%3A%20ACM%2C%202007.%20%3Ca%20class%3D%27zp-DOIURL%27%20href%3D%27https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F1316948.1316967%27%3Ehttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1145%5C%2F1316948.1316967%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3D3Y2LX8WJ%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Mining%20Geographic%20Knowledge%20Using%20Location%20Aware%20Topic%20Model%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chong%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jinggang%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xing%22%2C%22lastName%22%3A%22Xie%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wei-Ying%22%2C%22lastName%22%3A%22Ma%22%7D%5D%2C%22abstractNote%22%3A%22Most%20online%20activities%20are%20associated%20with%20geographical%20locations.%20For%20example%2C%20people%20write%20personal%20blogs%20about%20interesting%20places%20they%20have%20ever%20been%20to%3B%20read%20news%20about%20important%20local%20events%3B%20and%20search%20the%20web%20to%20find%20delicious%20restaurants.%20Mining%20geographical%20knowledge%20from%20these%20online%20activities%20can%20greatly%20benefit%20lots%20of%20web%20applications.%20This%20paper%20proposes%20a%20Location%20Aware%20Topic%20Model%20%28LATM%29%2C%20a%20probabilistic%20graphical%20model%2C%20to%20explicitly%20model%20the%20relationships%20between%20locations%20and%20words.%20Experiments%20on%20several%20data%20sets%2C%20including%20news%20and%20blogs%2C%20showed%20satisfactory%20results.%22%2C%22date%22%3A%222007%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%204th%20ACM%20Workshop%20on%20Geographical%20Information%20Retrieval%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1145%5C%2F1316948.1316967%22%2C%22ISBN%22%3A%22978-1-59593-828-2%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fdoi.acm.org%5C%2F10.1145%5C%2F1316948.1316967%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A43%3A47Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Mapping%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%2243TKXSYT%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Cao%20and%20Fei-Fei%22%2C%22parsedDate%22%3A%222007%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3ECao%2C%20L.%2C%20and%20Li%20Fei-Fei.%20%26%23x201C%3BSpatially%20Coherent%20Latent%20Topic%20Model%20for%20Concurrent%20Segmentation%20and%20Classification%20of%20Objects%20and%20Scenes.%26%23x201D%3B%20In%20%3Ci%3E2007%20IEEE%2011th%20International%20Conference%20on%20Computer%20Vision%3C%5C%2Fi%3E%2C%201%26%23x2013%3B8%2C%202007.%20%3Ca%20class%3D%27zp-DOIURL%27%20href%3D%27https%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FICCV.2007.4408965%27%3Ehttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FICCV.2007.4408965%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3D43TKXSYT%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Spatially%20Coherent%20Latent%20Topic%20Model%20for%20Concurrent%20Segmentation%20and%20Classification%20of%20Objects%20and%20Scenes%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22L.%22%2C%22lastName%22%3A%22Cao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Li%22%2C%22lastName%22%3A%22Fei-Fei%22%7D%5D%2C%22abstractNote%22%3A%22A%20novel%20generative%20model%20for%20simultaneously%20recognizing%20and%20segmenting%20object%20and%20scene%20classes%20that%20is%20inspired%20by%20the%20traditional%20bag%20of%20words%20representation%20of%20texts%20and%20images%20as%20well%20as%20a%20number%20of%20related%20generative%20models%2C%20including%20probabilistic%20latent%20semantic%20analysis%20%28pLSA%29%20and%20latent%20Dirichlet%20allocation%20%28LDA%29.%20This%20paper%20proposes%20a%20spatially%20coherent%20latent%20topic%20model%20%28spatial-LTM%29.%20Spatial-LTM%20represents%20an%20image%20containing%20objects%20in%20a%20hierarchical%20way%20by%20over-segmented%20image%20regions%20of%20homogeneous%20appearances%20and%20the%20salient%20image%20patches%20within%20the%20regions.%22%2C%22date%22%3A%222007%22%2C%22proceedingsTitle%22%3A%222007%20IEEE%2011th%20International%20Conference%20on%20Computer%20Vision%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1109%5C%2FICCV.2007.4408965%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A45%3A30Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20applied%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22HT2SPPCE%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Wang%20and%20Grimson%22%2C%22parsedDate%22%3A%222007%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EWang%2C%20Xiaogang%2C%20and%20Eric%20Grimson.%20%26%23x201C%3BSpatial%20Latent%20Dirichlet%20Allocation.%26%23x201D%3B%20In%20%3Ci%3EProceedings%20of%20the%2020th%20International%20Conference%20on%20Neural%20Information%20Processing%20Systems%3C%5C%2Fi%3E%2C%201577%26%23x2013%3B84.%20NIPS%26%23x2019%3B07.%20USA%3A%20Curran%20Associates%20Inc.%2C%202007.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27http%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fcitation.cfm%3Fid%3D2981562.2981760%27%3Ehttp%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fcitation.cfm%3Fid%3D2981562.2981760%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DHT2SPPCE%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Spatial%20Latent%20Dirichlet%20Allocation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaogang%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Eric%22%2C%22lastName%22%3A%22Grimson%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20proposes%20a%20topic%20model%20Spatial%20Latent%20Dirichlet%20Allocation%20%28SLDA%29%2C%20which%20better%20encodes%20spatial%20structures%20among%20visual%20words%20that%20are%20essential%20for%20solving%20many%20vision%20problems.%20The%20spatial%20information%20is%20not%20encoded%20in%20the%20values%20of%20visual%20words%20but%20in%20the%20design%20of%20documents.%20Instead%20of%20knowing%20the%20partition%20of%20words%20into%20documents%20a%20priori%2C%20the%20word-document%20assignment%20becomes%20a%20random%20hidden%20variable%20in%20SLDA.%20There%20is%20a%20generative%20procedure%2C%20where%20knowledge%20of%20spatial%20structure%20can%20be%20flexibly%20added%20as%20a%20prior%2C%20grouping%20visual%20words%20which%20are%20close%20in%20space%20into%20the%20same%20document.%22%2C%22date%22%3A%222007%22%2C%22proceedingsTitle%22%3A%22Proceedings%20of%20the%2020th%20International%20Conference%20on%20Neural%20Information%20Processing%20Systems%22%2C%22conferenceName%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22978-1-60560-352-0%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fdl.acm.org%5C%2Fcitation.cfm%3Fid%3D2981562.2981760%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A45%3A25Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%2C%7B%22key%22%3A%22S9DYQQQC%22%2C%22library%22%3A%7B%22id%22%3A2133649%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A22837%2C%22username%22%3A%22ayliu%22%2C%22name%22%3A%22Alan%20Liu%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fayliu%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22McCallum%20and%20Wang%22%2C%22parsedDate%22%3A%222006%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EMcCallum%2C%20Andrew%2C%20and%20Xuerui%20Wang.%20%3Ci%3ETopics%20over%20Time%3A%20A%20Non-Markov%20Continuous-Time%20Model%20of%20Topical%20Trends%3C%5C%2Fi%3E%2C%202006.%20%3Ca%20class%3D%27zp-ItemURL%27%20href%3D%27%5C%2Fpaper%5C%2FTopics-over-time%253A-a-non-Markov-continuous-time-of-Wang-McCallum%5C%2F7f8abf25ca24b48450b4e535f41e2b8a87df73f5%27%3E%5C%2Fpaper%5C%2FTopics-over-time%253A-a-non-Markov-continuous-time-of-Wang-McCallum%5C%2F7f8abf25ca24b48450b4e535f41e2b8a87df73f5%3C%5C%2Fa%3E.%20%3Ca%20title%3D%27Cite%20in%20RIS%20Format%27%20class%3D%27zp-CiteRIS%27%20href%3D%27https%3A%5C%2F%5C%2Fwe1s.ucsb.edu%5C%2Fwp-content%5C%2Fplugins%5C%2Fzotpress%5C%2Flib%5C%2Frequest%5C%2Frequest.cite.php%3Fapi_user_id%3D2133649%26amp%3Bitem_key%3DS9DYQQQC%27%3ECite%3C%5C%2Fa%3E%20%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22book%22%2C%22title%22%3A%22Topics%20over%20time%3A%20a%20non-Markov%20continuous-time%20model%20of%20topical%20trends%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrew%22%2C%22lastName%22%3A%22McCallum%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xuerui%22%2C%22lastName%22%3A%22Wang%22%7D%5D%2C%22abstractNote%22%3A%22This%20paper%20presents%20an%20LDA-style%20topic%20model%20that%20captures%20not%20only%20the%20low-dimensional%20structure%20of%20data%2C%20but%20also%20how%20the%20structure%20changes%20over%20time.%20Unlike%20other%20recent%20work%20that%20relies%20on%20Markov%20assumptions%20or%20discretization%20of%20time%2C%20here%20each%20topic%20is%20associated%20with%20a%20continuous%20distribution%20over%20timestamps%2C%20and%20for%20each%20generated%20document%2C%20the%20mixture%20distribution%20over%20topics%20is%20influenced%20by%20both%20word%20co-occurrences%20and%20the%20document%27s%20timestamp.%20Thus%2C%20the%20meaning%20of%20a%20particular%20topic%20can%20be%20relied%20upon%20as%20constant%2C%20but%20the%20topics%27%20occurrence%20and%20correlations%20change%20significantly%20over%20time.%20The%20presented%20results%20are%20on%20nine%20months%20of%20personal%20email%2C%2017%20years%20of%20NIPS%20research%20papers%20and%20over%20200%20years%20of%20presidential%20state-of-the-union%20addresses%2C%20showing%20improved%20topics%2C%20better%20timestamp%20prediction%2C%20and%20interpretable%20trends.%22%2C%22date%22%3A%222006%22%2C%22language%22%3A%22en%22%2C%22ISBN%22%3A%22%22%2C%22url%22%3A%22%5C%2Fpaper%5C%2FTopics-over-time%253A-a-non-Markov-continuous-time-of-Wang-McCallum%5C%2F7f8abf25ca24b48450b4e535f41e2b8a87df73f5%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222019-07-27T21%3A40%3A45Z%22%2C%22tags%22%3A%5B%7B%22tag%22%3A%22Topic%20model%20algorithm%22%7D%2C%7B%22tag%22%3A%22Topic%20model%20longitudinal%20over%20time%22%7D%2C%7B%22tag%22%3A%22Topic%20modeling%22%7D%5D%7D%7D%5D%7D
Guille, Adrien, and Edmundo-Pavel Soriano-Morales. “TOM: A Library for Topic Modeling and Browsing.” In Conférence Sur l’Extraction et La Gestion Des Connaissances. Actes de La 16ème Conférence Sur l’Extraction et La Gestion Des Connaissances. Reims, France, 2016. https://hal.archives-ouvertes.fr/hal-01442868. Cite
Vulić, Ivan, Wim De Smet, Jie Tang, and Marie-Francine Moens. “Probabilistic Topic Modeling in Multilingual Settings: An Overview of Its Methodology and Applications.” Information Processing & Management 51, no. 1 (2015): 111–47. http://keg.cs.tsinghua.edu.cn/jietang/publications/ipm15-xLiTe-IvanVulic-overview-topic-model-multilingual.pdf. Cite
Blei, David M. “Probabilistic Topic Models.” Communications of the ACM 55, no. 4 (2012): 77–84. https://doi.org/10.1145/2133806.2133826. Cite
Arora, Sanjeev, Rong Ge, Yoni Halpern, David Mimno, Ankur Moitra, David Sontag, Yichen Wu, and Michael Zhu. “A Practical Algorithm for Topic Modeling with Provable Guarantees.” ArXiv:1212.4777 [Cs, Stat], 2012. http://arxiv.org/abs/1212.4777. Cite
Wang, Chong, David Blei, and David Heckerman. “Continuous Time Dynamic Topic Models.” ArXiv:1206.3298 [Cs, Stat], 2012. http://arxiv.org/abs/1206.3298. Cite
Wu, Hao, Jiajun Bu, Chun Chen, Jianke Zhu, Lijun Zhang, Haifeng Liu, Can Wang, and Deng Cai. “Locally Discriminative Topic Modeling.” Pattern Recognition 45, no. 1 (2012): 617–25. https://doi.org/10.1016/j.patcog.2011.04.029. Cite
Ponweiser, Martin. “Latent Dirichlet Allocation in R.” Diploma Thesis, Vienna University of Economics and Business, 2012. http://epub.wu.ac.at/3558/. Cite
Boyd-Graber, Jordan, and Philip Resnik. “Holistic Sentiment Analysis across Languages: Multilingual Supervised Latent Dirichlet Allocation.” In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, 45–55. Association for Computational Linguistics, 2010. http://www.aclweb.org/anthology/D10-1005. Cite
Saria, Suchi, Daphne Koller, and Anna Penn. “Discovering Shared and Individual Latent Structure in Multiple Time Series.” ArXiv:1008.2028 [Cs, Stat], 2010. http://arxiv.org/abs/1008.2028. Cite
Andrews, Mark, and Gabriella Vigliocco. “The Hidden Markov Topic Model: A Probabilistic Model of Semantic Representation.” Topics in Cognitive Science 2, no. 1 (2010): 101–13. https://onlinelibrary.wiley.com/doi/pdf/10.1111/j.1756-8765.2009.01074.x. Cite
Wallach, Hanna M., David Mimno, and Andrew McCallum. “Rethinking LDA: Why Priors Matter.” In Proceedings of the 22Nd International Conference on Neural Information Processing Systems, 1973–81. NIPS’09. USA: Curran Associates Inc., 2009. http://dl.acm.org/citation.cfm?id=2984093.2984314. Cite
Ramage, Daniel, David Hall, Ramesh Nallapati, and Christopher D. Manning. “Labeled LDA: A Supervised Topic Model for Credit Attribution in Multi-Labeled Corpora.” In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1, 248–56. EMNLP ’09. Stroudsburg, PA, USA: Association for Computational Linguistics, 2009. http://dl.acm.org/citation.cfm?id=1699510.1699543. Cite
Boyd-Graber, Jordan, and David M. Blei. “Multilingual Topic Models for Unaligned Text.” In Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, 75–82. AUAI Press, 2009. https://arxiv.org/pdf/1205.2657. Cite
Boyd-Graber, Jordan L., and David M. Blei. “Syntactic Topic Models.” In Advances in Neural Information Processing Systems, 185–92, 2009. https://papers.nips.cc/paper/3398-syntactic-topic-models.pdf. Cite
Boyd-Graber, Jordan, David Blei, and Xiaojin Zhu. “A Topic Model for Word Sense Disambiguation.” In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 1024–33, 2007. http://www.aclweb.org/anthology/D07-1109. Cite
Rosen-Zvi, Michal, Yair Weiss, and Amit Gruber. “Hidden Topic Markov Models.” In Artificial Intelligence and Statistics, 163–70, 2007. http://proceedings.mlr.press/v2/gruber07a.html. Cite
Wang, Chong, Jinggang Wang, Xing Xie, and Wei-Ying Ma. “Mining Geographic Knowledge Using Location Aware Topic Model.” In Proceedings of the 4th ACM Workshop on Geographical Information Retrieval, 65–70. GIR ’07. New York, NY, USA: ACM, 2007. https://doi.org/10.1145/1316948.1316967. Cite
Cao, L., and Li Fei-Fei. “Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes.” In 2007 IEEE 11th International Conference on Computer Vision, 1–8, 2007. https://doi.org/10.1109/ICCV.2007.4408965. Cite
Wang, Xiaogang, and Eric Grimson. “Spatial Latent Dirichlet Allocation.” In Proceedings of the 20th International Conference on Neural Information Processing Systems, 1577–84. NIPS’07. USA: Curran Associates Inc., 2007. http://dl.acm.org/citation.cfm?id=2981562.2981760. Cite
McCallum, Andrew, and Xuerui Wang. Topics over Time: A Non-Markov Continuous-Time Model of Topical Trends, 2006. /paper/Topics-over-time%3A-a-non-Markov-continuous-time-of-Wang-McCallum/7f8abf25ca24b48450b4e535f41e2b8a87df73f5. Cite