{"id":"https://openalex.org/W2525539774","doi":"https://doi.org/10.18653/v1/d16-1099","title":"The Effects of Data Size and Frequency Range on Distributional Semantic Models","display_name":"The Effects of Data Size and Frequency Range on Distributional Semantic Models","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2525539774","doi":"https://doi.org/10.18653/v1/d16-1099","mag":"2525539774"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d16-1099","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1099","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 2016 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/d16-1099","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058048696","display_name":"Magnus Sahlgren","orcid":"https://orcid.org/0000-0001-5100-0535"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Magnus Sahlgren","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050795259","display_name":"Alessandro Lenci","orcid":"https://orcid.org/0000-0001-5790-4308"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alessandro Lenci","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058048696"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.998,"has_fulltext":false,"cited_by_count":109,"citation_normalized_percentile":{"value":0.97855555,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"975","last_page":"980"},"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":0.9994000196456909,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9919000267982483,"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/range","display_name":"Range (aeronautics)","score":0.7626663446426392},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6506122946739197},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5185371041297913},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.41418203711509705},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4119333028793335},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39336249232292175},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.33461323380470276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30420053005218506},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19647380709648132},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0671461820602417}],"concepts":[{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.7626663446426392},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6506122946739197},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5185371041297913},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.41418203711509705},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4119333028793335},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39336249232292175},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.33461323380470276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30420053005218506},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19647380709648132},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0671461820602417},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d16-1099","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1099","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 2016 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d16-1099","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1099","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 2016 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W124633754","https://openalex.org/W1534993021","https://openalex.org/W1584739173","https://openalex.org/W1615991656","https://openalex.org/W1854884267","https://openalex.org/W1966907789","https://openalex.org/W1983578042","https://openalex.org/W1992009922","https://openalex.org/W2110485445","https://openalex.org/W2112184938","https://openalex.org/W2117130368","https://openalex.org/W2153579005","https://openalex.org/W2250189634","https://openalex.org/W2251012068","https://openalex.org/W2251093660","https://openalex.org/W2252211741","https://openalex.org/W2577417694","https://openalex.org/W2787086582","https://openalex.org/W3154772965"],"related_works":["https://openalex.org/W2391251536","https://openalex.org/W2362198218","https://openalex.org/W1982750869","https://openalex.org/W2019521278","https://openalex.org/W1984922432","https://openalex.org/W2375008505","https://openalex.org/W3167905444","https://openalex.org/W3092431721","https://openalex.org/W3195353062","https://openalex.org/W3186268266"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,17,50,56,69],"effects":[4],"of":[5,19,22,31,38,62],"data":[6,30,51,61],"size":[7],"and":[8,34,54,65],"frequency":[9,66],"range":[10],"on":[11],"distributional":[12],"semantic":[13],"models.":[14],"We":[15],"compare":[16],"performance":[18],"a":[20],"number":[21],"representative":[23],"models":[24,47],"for":[25],"several":[26],"test":[27,36],"settings":[28],"over":[29,35,60],"varying":[32,63],"sizes,":[33],"items":[37],"various":[39],"frequency.":[40],"Our":[41],"results":[42],"show":[43],"that":[44,55],"neural":[45],"network-based":[46],"underperform":[48],"when":[49],"is":[52,68],"small,":[53],"most":[57],"reliable":[58],"model":[59],"sizes":[64],"ranges":[67],"inverted":[70],"factorized":[71],"model.":[72]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":39},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}