{"id":"https://openalex.org/W2963676655","doi":"https://doi.org/10.18653/v1/p18-1221","title":"Building Language Models for Text with Named Entities","display_name":"Building Language Models for Text with Named Entities","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2963676655","doi":"https://doi.org/10.18653/v1/p18-1221","mag":"2963676655"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1221","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1221","pdf_url":"https://www.aclweb.org/anthology/P18-1221.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-1221.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020616425","display_name":"Md Rizwan Parvez","orcid":"https://orcid.org/0000-0002-3708-7803"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Rizwan Parvez","raw_affiliation_strings":["University of California Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074368173","display_name":"Saikat Chakraborty","orcid":"https://orcid.org/0000-0002-6889-7171"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saikat Chakraborty","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064541855","display_name":"Baishakhi Ray","orcid":"https://orcid.org/0000-0003-3406-5235"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baishakhi Ray","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087096372","display_name":"Kai-Wei Chang","orcid":"https://orcid.org/0000-0001-5365-0072"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai-Wei Chang","raw_affiliation_strings":["University of California Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2373","last_page":"2383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T11719","display_name":"Data Quality and Management","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.9575144052505493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8924932479858398},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.73457270860672},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6663299202919006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6419615745544434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6075460910797119},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.518325924873352},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5042575597763062},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4644607901573181},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.42251256108283997}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9575144052505493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8924932479858398},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.73457270860672},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6663299202919006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6419615745544434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6075460910797119},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.518325924873352},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5042575597763062},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4644607901573181},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.42251256108283997},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-1221","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1221","pdf_url":"https://www.aclweb.org/anthology/P18-1221.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1221","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1221","pdf_url":"https://www.aclweb.org/anthology/P18-1221.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4385247538","display_name":"CRII: RI: Learning Structured Prediction Models with Auxiliary Supervision","funder_award_id":"1760523","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963676655.pdf","grobid_xml":"https://content.openalex.org/works/W2963676655.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W36903255","https://openalex.org/W179875071","https://openalex.org/W249480477","https://openalex.org/W1522301498","https://openalex.org/W1580723896","https://openalex.org/W1988346254","https://openalex.org/W1990365157","https://openalex.org/W2056964940","https://openalex.org/W2057900969","https://openalex.org/W2064580901","https://openalex.org/W2074529754","https://openalex.org/W2100714283","https://openalex.org/W2121227244","https://openalex.org/W2127314673","https://openalex.org/W2142403498","https://openalex.org/W2142958724","https://openalex.org/W2143861926","https://openalex.org/W2143960295","https://openalex.org/W2165747537","https://openalex.org/W2250539671","https://openalex.org/W2259472270","https://openalex.org/W2342082360","https://openalex.org/W2344444819","https://openalex.org/W2507756961","https://openalex.org/W2561658355","https://openalex.org/W2728599219","https://openalex.org/W2735651482","https://openalex.org/W2740130862","https://openalex.org/W2743945814","https://openalex.org/W2761670104","https://openalex.org/W2949417144","https://openalex.org/W2951813108","https://openalex.org/W2962728167","https://openalex.org/W2963094819","https://openalex.org/W2963617989","https://openalex.org/W2963925965","https://openalex.org/W2963935794","https://openalex.org/W2964121744","https://openalex.org/W2964165364","https://openalex.org/W3003280364","https://openalex.org/W3005855585","https://openalex.org/W4255398023","https://openalex.org/W4299838440"],"related_works":["https://openalex.org/W1989705153","https://openalex.org/W2496228846","https://openalex.org/W2259472270","https://openalex.org/W2896411932","https://openalex.org/W2131111393","https://openalex.org/W59929963","https://openalex.org/W3107474891","https://openalex.org/W2972969579","https://openalex.org/W2970986510","https://openalex.org/W4288112129"],"abstract_inverted_index":{"Text":[0],"in":[1,89],"many":[2],"domains":[3],"involves":[4],"a":[5,19,36,43],"significant":[6],"amount":[7],"of":[8],"named":[9],"entities.":[10],"Predicting":[11],"the":[12,28,50,76,98],"entity":[13,51,56],"names":[14,52],"is":[15],"often":[16],"challenging":[17],"for":[18],"language":[20,45,100],"model":[21,46,84],"as":[22],"they":[23],"appear":[24],"less":[25],"frequent":[26],"on":[27,66,72,94],"training":[29],"corpus.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,74],"propose":[35],"novel":[37],"and":[38,68,92],"effective":[39],"approach":[40],"to":[41],"building":[42],"discriminative":[44],"which":[47,73],"can":[48],"learn":[49],"by":[53],"leveraging":[54],"their":[55],"type":[57],"information.":[58],"We":[59],"also":[60],"introduce":[61],"two":[62],"benchmark":[63],"datasets":[64],"based":[65],"recipes":[67],"Java":[69],"programming":[70],"codes,":[71],"evaluate":[75],"proposed":[77],"model.":[78],"Experimental":[79],"results":[80],"show":[81],"that":[82],"our":[83],"achieves":[85],"52.2%":[86],"better":[87],"perplexity":[88],"recipe":[90],"generation":[91,96],"22.06%":[93],"code":[95],"than":[97],"stateof-the-art":[99],"models.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}