{"id":"https://openalex.org/W2929208326","doi":"https://doi.org/10.18653/v1/n19-1149","title":"Using Similarity Measures to Select Pretraining Data for","display_name":"Using Similarity Measures to Select Pretraining Data for","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2929208326","doi":"https://doi.org/10.18653/v1/n19-1149","mag":"2929208326"},"language":"en","primary_location":{"id":"doi:10.18653/v1/n19-1149","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n19-1149","pdf_url":null,"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 2019 Conference of the North","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/n19-1149","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101585101","display_name":"Xiang Dai","orcid":"https://orcid.org/0000-0002-6020-9688"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041251183","display_name":"Sarvnaz Karimi","orcid":"https://orcid.org/0000-0002-4927-3937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sarvnaz Karimi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088816085","display_name":"Ben Hachey","orcid":"https://orcid.org/0000-0001-7237-2127"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Hachey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077002072","display_name":"C\u00e9cile Paris","orcid":"https://orcid.org/0000-0003-3816-0176"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cecile Paris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3896,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.94461249,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T11550","display_name":"Text and Document Classification Technologies","score":0.9958000183105469,"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/similarity","display_name":"Similarity (geometry)","score":0.7796030044555664},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.5928146243095398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5853404998779297},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5750274062156677},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.5702661275863647},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.5379707217216492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48748230934143066},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32930076122283936},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32042163610458374},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1723322868347168},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09368309378623962},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06437927484512329}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7796030044555664},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.5928146243095398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5853404998779297},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5750274062156677},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.5702661275863647},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.5379707217216492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48748230934143066},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32930076122283936},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32042163610458374},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1723322868347168},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09368309378623962},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06437927484512329},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/n19-1149","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n19-1149","pdf_url":null,"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 2019 Conference of the North","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/n19-1149","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n19-1149","pdf_url":null,"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 2019 Conference of the North","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1539309091","https://openalex.org/W1614298861","https://openalex.org/W1615991656","https://openalex.org/W1840435438","https://openalex.org/W1854884267","https://openalex.org/W1940872118","https://openalex.org/W1975879668","https://openalex.org/W1984186257","https://openalex.org/W2001180667","https://openalex.org/W2040298461","https://openalex.org/W2047782770","https://openalex.org/W2131546905","https://openalex.org/W2134800885","https://openalex.org/W2136930489","https://openalex.org/W2144578941","https://openalex.org/W2158108973","https://openalex.org/W2158139315","https://openalex.org/W2170571488","https://openalex.org/W2170973209","https://openalex.org/W2250539671","https://openalex.org/W2251882135","https://openalex.org/W2251908874","https://openalex.org/W2259472270","https://openalex.org/W2296283641","https://openalex.org/W2329847998","https://openalex.org/W2396881363","https://openalex.org/W2515248967","https://openalex.org/W2739515596","https://openalex.org/W2785674115","https://openalex.org/W2798575764","https://openalex.org/W2880875857","https://openalex.org/W2882319491","https://openalex.org/W2927746189","https://openalex.org/W2927881688","https://openalex.org/W2962739339","https://openalex.org/W2962755455","https://openalex.org/W2962772361","https://openalex.org/W2962798796","https://openalex.org/W2962902328","https://openalex.org/W2962903510","https://openalex.org/W2963012544","https://openalex.org/W2963341956","https://openalex.org/W2963418282","https://openalex.org/W2963494889","https://openalex.org/W2963558636","https://openalex.org/W2963563735","https://openalex.org/W2963641259","https://openalex.org/W2964046515","https://openalex.org/W2964068917"],"related_works":["https://openalex.org/W2798121181","https://openalex.org/W2352440174","https://openalex.org/W4309440960","https://openalex.org/W2016805743","https://openalex.org/W4242592912","https://openalex.org/W435830328","https://openalex.org/W2062168445","https://openalex.org/W2087896742","https://openalex.org/W2348940229","https://openalex.org/W2363046693"],"abstract_inverted_index":{"Xiang":[0],"Dai,":[1],"Sarvnaz":[2],"Karimi,":[3],"Ben":[4],"Hachey,":[5],"Cecile":[6],"Paris.":[7],"Proceedings":[8],"of":[9,13,18],"the":[10,14,19],"2019":[11],"Conference":[12],"North":[15],"American":[16],"Chapter":[17],"Association":[20],"for":[21],"Computational":[22],"Linguistics:":[23],"Human":[24],"Language":[25],"Technologies,":[26],"Volume":[27],"1":[28],"(Long":[29],"and":[30],"Short":[31],"Papers).":[32],"2019.":[33]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
