@incollection{Blei/etal:04,
	address = {Cambridge, MA},
	title = {Integrating topics and syntax},
	abstract = {Statistical approaches to language learning typically focus on either
short-range syntactic dependencies or long-range semantic dependencies
between words. We present a generative model that uses both kinds of
dependencies, and is capable of simultaneously finding syntactic classes
and semantic topics despite having no knowledge of syntax or semantics
beyond statistical dependency. This model is competitive on tasks
like part-of-speech tagging and document classification with models that
exclusively use short- and long-range dependencies respectively.},
	booktitle = {Advances in {Neural} {Information} {Processing} {Systems} 17},
	publisher = {MIT Press},
	author = {Blei, David M and Griffiths, Thomas L and Jordan, Michael I and Tenenbaum, Joshua B},
	year = {2004},
}

{"_id":"5rDw89iqskgmZhMT7","bibbaseid":"blei-griffiths-jordan-tenenbaum-integratingtopicsandsyntax-2004","author_short":["Blei, D. M","Griffiths, T. L","Jordan, M. I","Tenenbaum, J. B"],"bibdata":{"bibtype":"incollection","type":"incollection","address":"Cambridge, MA","title":"Integrating topics and syntax","abstract":"Statistical approaches to language learning typically focus on either short-range syntactic dependencies or long-range semantic dependencies between words. We present a generative model that uses both kinds of dependencies, and is capable of simultaneously finding syntactic classes and semantic topics despite having no knowledge of syntax or semantics beyond statistical dependency. This model is competitive on tasks like part-of-speech tagging and document classification with models that exclusively use short- and long-range dependencies respectively.","booktitle":"Advances in Neural Information Processing Systems 17","publisher":"MIT Press","author":[{"propositions":[],"lastnames":["Blei"],"firstnames":["David","M"],"suffixes":[]},{"propositions":[],"lastnames":["Griffiths"],"firstnames":["Thomas","L"],"suffixes":[]},{"propositions":[],"lastnames":["Jordan"],"firstnames":["Michael","I"],"suffixes":[]},{"propositions":[],"lastnames":["Tenenbaum"],"firstnames":["Joshua","B"],"suffixes":[]}],"year":"2004","bibtex":"@incollection{Blei/etal:04,\n\taddress = {Cambridge, MA},\n\ttitle = {Integrating topics and syntax},\n\tabstract = {Statistical approaches to language learning typically focus on either\nshort-range syntactic dependencies or long-range semantic dependencies\nbetween words. We present a generative model that uses both kinds of\ndependencies, and is capable of simultaneously finding syntactic classes\nand semantic topics despite having no knowledge of syntax or semantics\nbeyond statistical dependency. This model is competitive on tasks\nlike part-of-speech tagging and document classification with models that\nexclusively use short- and long-range dependencies respectively.},\n\tbooktitle = {Advances in {Neural} {Information} {Processing} {Systems} 17},\n\tpublisher = {MIT Press},\n\tauthor = {Blei, David M and Griffiths, Thomas L and Jordan, Michael I and Tenenbaum, Joshua B},\n\tyear = {2004},\n}\n\n","author_short":["Blei, D. M","Griffiths, T. L","Jordan, M. I","Tenenbaum, J. B"],"key":"Blei/etal:04","id":"Blei/etal:04","bibbaseid":"blei-griffiths-jordan-tenenbaum-integratingtopicsandsyntax-2004","role":"author","urls":{},"metadata":{"authorlinks":{}},"html":""},"bibtype":"incollection","biburl":"https://bibbase.org/zotero/ifromm","dataSources":["N4kJAiLiJ7kxfNsoh"],"keywords":[],"search_terms":["integrating","topics","syntax","blei","griffiths","jordan","tenenbaum"],"title":"Integrating topics and syntax","year":2004}