{"id":"https://openalex.org/W2136515308","doi":"https://doi.org/10.3115/1075096.1075162","title":"Unsupervised learning of dependency structure for language modeling","display_name":"Unsupervised learning of dependency structure for language modeling","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2136515308","doi":"https://doi.org/10.3115/1075096.1075162","mag":"2136515308"},"language":"en","primary_location":{"id":"doi:10.3115/1075096.1075162","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075096.1075162","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075162","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st Annual Meeting on Association for Computational Linguistics  - ACL '03","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075162","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100887075","display_name":"Hisami Suzuki","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hisami Suzuki","raw_affiliation_strings":["Microsoft Research, Redmond WA","Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7507,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93600771,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"521","last_page":"528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.7953464388847351},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.794715166091919},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7162374258041382},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6752195954322815},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6293736100196838},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6099648475646973},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.5835630893707275},{"id":"https://openalex.org/keywords/dependency-grammar","display_name":"Dependency grammar","score":0.5377203822135925},{"id":"https://openalex.org/keywords/dependency-graph","display_name":"Dependency graph","score":0.5272183418273926},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4691884517669678},{"id":"https://openalex.org/keywords/kanji","display_name":"Kanji","score":0.4652351438999176},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4547599256038666},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4228641986846924},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.349905788898468},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2039746642112732},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1492551565170288}],"concepts":[{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.7953464388847351},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794715166091919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7162374258041382},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6752195954322815},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6293736100196838},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6099648475646973},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.5835630893707275},{"id":"https://openalex.org/C164883195","wikidata":"https://www.wikidata.org/wiki/Q674834","display_name":"Dependency grammar","level":3,"score":0.5377203822135925},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.5272183418273926},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4691884517669678},{"id":"https://openalex.org/C83535845","wikidata":"https://www.wikidata.org/wiki/Q82772","display_name":"Kanji","level":3,"score":0.4652351438999176},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4547599256038666},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4228641986846924},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.349905788898468},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2039746642112732},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1492551565170288},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/1075096.1075162","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075096.1075162","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075162","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st Annual Meeting on Association for Computational Linguistics  - ACL '03","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.77.7876","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.77.7876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/acl2003/main/ps/GaoSuzuki.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.78.9923","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.78.9923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/acl2003/main/pdfs/GaoSuzuki.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1075096.1075162","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075096.1075162","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1075096.1075162","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st Annual Meeting on Association for Computational Linguistics  - ACL '03","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2136515308.pdf","grobid_xml":"https://content.openalex.org/works/W2136515308.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1590952807","https://openalex.org/W1607229519","https://openalex.org/W1974967573","https://openalex.org/W1989705153","https://openalex.org/W2005614013","https://openalex.org/W2096466920","https://openalex.org/W2110882317","https://openalex.org/W2123893795","https://openalex.org/W2125838338","https://openalex.org/W2134237567","https://openalex.org/W2153208746","https://openalex.org/W2155693943","https://openalex.org/W4253573210","https://openalex.org/W4255764218","https://openalex.org/W4300925921","https://openalex.org/W6601443004"],"related_works":["https://openalex.org/W2105076537","https://openalex.org/W2020757772","https://openalex.org/W2072223048","https://openalex.org/W2041167939","https://openalex.org/W2950575438","https://openalex.org/W2002221802","https://openalex.org/W2250909759","https://openalex.org/W1975573722","https://openalex.org/W1620568205","https://openalex.org/W1823613926"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,13,17,32,74,77,87],"dependency":[4,14,48,71],"language":[5,53],"model":[6,54],"(DLM)":[7],"that":[8,22,68,95],"captures":[9],"linguistic":[10],"constraints":[11],"via":[12],"structure,":[15],"i.e.,":[16],"set":[18],"of":[19,28,73],"probabilistic":[20],"dependencies":[21],"express":[23],"the":[24,47,70,83,96,106],"relations":[25],"between":[26],"headwords":[27],"each":[29],"phrase":[30],"in":[31],"sentence":[33,75],"by":[34],"an":[35,51,64,100],"acyclic,":[36],"planar,":[37],"undirected":[38],"graph.":[39],"Our":[40],"contributions":[41],"are":[42],"three-fold.":[43],"First,":[44],"we":[45,62,81],"incorporate":[46],"structure":[49,72],"into":[50],"n-gram":[52],"to":[55],"capture":[56],"long":[57],"distance":[58],"word":[59,107],"dependency.":[60],"Second,":[61],"present":[63],"unsupervised":[65],"learning":[66],"method":[67],"discovers":[69],"using":[76],"bootstrapping":[78],"procedure.":[79],"Finally,":[80],"evaluate":[82],"proposed":[84],"models":[85],"on":[86],"realistic":[88],"application":[89],"(Japanese":[90],"Kana-Kanji":[91],"conversion).":[92],"Experiments":[93],"show":[94],"best":[97],"DLM":[98],"achieves":[99],"11.3%":[101],"error":[102],"rate":[103],"reduction":[104],"over":[105],"trigram":[108],"model.":[109]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}