{"id":"https://openalex.org/W4245721198","doi":"https://doi.org/10.18653/v1/w16-2902","title":"Improved Semantic Representation for Domain-Specific Entities","display_name":"Improved Semantic Representation for Domain-Specific Entities","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W4245721198","doi":"https://doi.org/10.18653/v1/w16-2902"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2902","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2902","pdf_url":"https://www.aclweb.org/anthology/W16-2902.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 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-2902.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091017313","display_name":"Mohammad Taher Pilehvar","orcid":"https://orcid.org/0000-0003-3694-4006"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Mohammad Taher Pilehvar","raw_affiliation_strings":["Language Technology Lab Department of Theoretical and Applied Linguistics University of Cambridge Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Language Technology Lab Department of Theoretical and Applied Linguistics University of Cambridge Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073413742","display_name":"Nigel Collier","orcid":"https://orcid.org/0000-0002-7230-4164"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nigel Collier","raw_affiliation_strings":["Language Technology Lab Department of Theoretical and Applied Linguistics University of Cambridge Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Language Technology Lab Department of Theoretical and Applied Linguistics University of Cambridge Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091017313"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.4417,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82931151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"16"},"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8332014679908752},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.8025525212287903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6762193441390991},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6499536037445068},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6320428848266602},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6177916526794434},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5922415256500244},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5821122527122498},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5257214903831482},{"id":"https://openalex.org/keywords/lexical-item","display_name":"Lexical item","score":0.4377526044845581},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3710182309150696},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17483243346214294},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08601468801498413},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07183453440666199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8332014679908752},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.8025525212287903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6762193441390991},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6499536037445068},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6320428848266602},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6177916526794434},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5922415256500244},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5821122527122498},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5257214903831482},{"id":"https://openalex.org/C126706616","wikidata":"https://www.wikidata.org/wiki/Q2944660","display_name":"Lexical item","level":2,"score":0.4377526044845581},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3710182309150696},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17483243346214294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08601468801498413},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07183453440666199},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w16-2902","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2902","pdf_url":"https://www.aclweb.org/anthology/W16-2902.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 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2902","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2902","pdf_url":"https://www.aclweb.org/anthology/W16-2902.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 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2663634960","display_name":"PheneBank: automatic extraction and validation of a database of human phenotype-disease associations in the scientific literature","funder_award_id":"MR/M025160/1","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4245721198.pdf","grobid_xml":"https://content.openalex.org/works/W4245721198.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W68293321","https://openalex.org/W1503259811","https://openalex.org/W1608322251","https://openalex.org/W1614298861","https://openalex.org/W2029054018","https://openalex.org/W2120699290","https://openalex.org/W2125786288","https://openalex.org/W2127289991","https://openalex.org/W2162456950","https://openalex.org/W2164019165","https://openalex.org/W2164973920","https://openalex.org/W2170282111","https://openalex.org/W2192710297","https://openalex.org/W2250418535","https://openalex.org/W2250539671","https://openalex.org/W2250930514","https://openalex.org/W2250954350","https://openalex.org/W2251044566","https://openalex.org/W2251537235","https://openalex.org/W2251771443"],"related_works":["https://openalex.org/W947140380","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W4214830338","https://openalex.org/W2518587255","https://openalex.org/W4287599800","https://openalex.org/W4385432812"],"abstract_inverted_index":{"Most":[0],"existing":[1],"corpus-based":[2],"approaches":[3],"to":[4,45],"semantic":[5],"representation":[6],"suffer":[7],"from":[8],"inaccurate":[9],"modeling":[10,54,82],"of":[11,49,61,75,85],"domain-specific":[12],"lexical":[13,43,86],"items":[14,87],"which":[15],"either":[16],"have":[17],"low":[18],"frequencies":[19],"or":[20],"are":[21],"non-existent":[22],"in":[23,35,88],"open-domain":[24],"corpora.":[25],"We":[26],"put":[27],"forward":[28],"a":[29,41,46,83],"technique":[30,70],"that":[31,67],"improves":[32],"word":[33,78],"embeddings":[34,60],"specific":[36],"domains":[37],"by":[38,57],"first":[39],"transforming":[40],"given":[42],"item":[44,56],"sorted":[47],"list":[48],"representative":[50],"words":[51],"and":[52],"then":[53],"the":[55,59,68,76,89],"combining":[58],"these":[62],"words.":[63],"Our":[64],"experiments":[65],"show":[66],"proposed":[69],"can":[71],"significantly":[72],"improve":[73],"some":[74],"recent":[77],"embedding":[79],"techniques":[80],"while":[81],"set":[84],"biomedical":[90],"domain,":[91],"i.e.,":[92],"phenotypes.":[93]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}