{"id":"https://openalex.org/W2040942848","doi":"https://doi.org/10.3115/1117794.1117804","title":"Nonlocal language modeling based on context co-occurrence vectors","display_name":"Nonlocal language modeling based on context co-occurrence vectors","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W2040942848","doi":"https://doi.org/10.3115/1117794.1117804","mag":"2040942848"},"language":"en","primary_location":{"id":"doi:10.3115/1117794.1117804","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1117794.1117804","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1117794.1117804","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics -","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/10.3115/1117794.1117804","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028836340","display_name":"Sadao Kurohashi","orcid":"https://orcid.org/0000-0001-5398-8399"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Sadao Kurohashi","raw_affiliation_strings":["Kyoto University, Yoshida-honmachi, Sakyo, Kyoto, Japan","Kyoto University, Yoshida honmachi, Sakyo, Kyoto, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Yoshida-honmachi, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Yoshida honmachi, Sakyo, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055118976","display_name":"Manabu Ori","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Manabu Ori","raw_affiliation_strings":["Kyoto University, Yoshida-honmachi, Sakyo, Kyoto, Japan","Kyoto University, Yoshida honmachi, Sakyo, Kyoto, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Yoshida-honmachi, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Yoshida honmachi, Sakyo, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028836340"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11956547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"80","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9918000102043152,"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/perplexity","display_name":"Perplexity","score":0.9223265647888184},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7739951610565186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.747187614440918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6460869908332825},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.616733193397522},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.607896625995636},{"id":"https://openalex.org/keywords/co-occurrence","display_name":"Co-occurrence","score":0.5777056813240051},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5506510138511658},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5478690266609192},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5235999822616577},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.46417710185050964},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.45358991622924805},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4158720076084137},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19955527782440186},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.16532158851623535},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13494324684143066}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9223265647888184},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7739951610565186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.747187614440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6460869908332825},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.616733193397522},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.607896625995636},{"id":"https://openalex.org/C154290570","wikidata":"https://www.wikidata.org/wiki/Q1756768","display_name":"Co-occurrence","level":2,"score":0.5777056813240051},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5506510138511658},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5478690266609192},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5235999822616577},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.46417710185050964},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.45358991622924805},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4158720076084137},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19955527782440186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.16532158851623535},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13494324684143066},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1117794.1117804","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1117794.1117804","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1117794.1117804","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics -","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.416.299","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.416.299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.jhu.edu/~yarowsky/acl2000/sigdat/kurohashi.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1117794.1117804","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1117794.1117804","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1117794.1117804","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics -","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7752643416","display_name":null,"funder_award_id":"Japan","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2040942848.pdf","grobid_xml":"https://content.openalex.org/works/W2040942848.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W166966826","https://openalex.org/W2070474806","https://openalex.org/W2102439588","https://openalex.org/W2125489263","https://openalex.org/W2127836646","https://openalex.org/W2141645663","https://openalex.org/W2147152072","https://openalex.org/W2156202195","https://openalex.org/W3022556212"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W4287323699","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467","https://openalex.org/W2787311093"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,37],"novel":[4],"nonlocal":[5],"language":[6],"model":[7,16],"which":[8],"utilizes":[9],"contextual":[10],"information.":[11],"A":[12],"reduced":[13],"vector":[14,46],"space":[15],"calculated":[17],"from":[18],"co-occurrences":[19],"of":[20,29,36],"word":[21,24,30,49],"pairs":[22],"provides":[23],"co-occurrence":[25,31,50],"vectors.":[26],"The":[27],"sum":[28],"vectors":[32,51],"represents":[33,52],"the":[34,40,44,48,53,59],"context":[35,45],"document,":[38],"and":[39,47,70],"cosine":[41],"similarity":[42],"between":[43],"long-distance":[54],"lexical":[55],"dependencies.":[56],"Experiments":[57],"on":[58,72],"Mainichi":[60],"Newspaper":[61],"corpus":[62],"show":[63],"significant":[64],"improvement":[65],"in":[66],"perplexity":[67],"(5.0%":[68],"overall":[69],"27.2%":[71],"target":[73],"vocabulary)":[74]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}