{"id":"https://openalex.org/W4316192634","doi":"https://doi.org/10.1145/3574318.3574346","title":"\u201cIf you can\u2019t beat them, join them\u201d: A Word Transformation based Generalized Skip-gram for Embedding Compound Words","display_name":"\u201cIf you can\u2019t beat them, join them\u201d: A Word Transformation based Generalized Skip-gram for Embedding Compound Words","publication_year":2022,"publication_date":"2022-12-09","ids":{"openalex":"https://openalex.org/W4316192634","doi":"https://doi.org/10.1145/3574318.3574346"},"language":"en","primary_location":{"id":"doi:10.1145/3574318.3574346","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3574318.3574346","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3574318.3574346","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Annual Meeting of the Forum for Information Retrieval Evaluation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3574318.3574346","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082339849","display_name":"Debasis Ganguly","orcid":"https://orcid.org/0000-0003-0050-7138"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Debasis Ganguly","raw_affiliation_strings":["University of Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-0050-7138","affiliations":[{"raw_affiliation_string":"University of Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086918282","display_name":"Shripad Bhat","orcid":"https://orcid.org/0000-0002-4666-6882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shripad Bhat","raw_affiliation_strings":["Edvak Health Private Limited, India"],"raw_orcid":"https://orcid.org/0000-0002-4666-6882","affiliations":[{"raw_affiliation_string":"Edvak Health Private Limited, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037394429","display_name":"C. Biswas","orcid":"https://orcid.org/0000-0003-4468-7396"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chandan Biswas","raw_affiliation_strings":["Tatras Data, India"],"raw_orcid":"https://orcid.org/0000-0003-4468-7396","affiliations":[{"raw_affiliation_string":"Tatras Data, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.506,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66114632,"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":"34","last_page":"42"},"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9959999918937683,"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/word2vec","display_name":"Word2vec","score":0.81268709897995},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.776578426361084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7636309862136841},{"id":"https://openalex.org/keywords/compounding","display_name":"Compounding","score":0.6649469137191772},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6240066885948181},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6076690554618835},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6043831706047058},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5647861361503601},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4521501362323761},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16893914341926575},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09624519944190979}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.81268709897995},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.776578426361084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7636309862136841},{"id":"https://openalex.org/C207673951","wikidata":"https://www.wikidata.org/wiki/Q1303150","display_name":"Compounding","level":2,"score":0.6649469137191772},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6240066885948181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6076690554618835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6043831706047058},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5647861361503601},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4521501362323761},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16893914341926575},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09624519944190979},{"id":"https://openalex.org/C159110408","wikidata":"https://www.wikidata.org/wiki/Q121176","display_name":"Nursing","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},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3574318.3574346","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3574318.3574346","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3574318.3574346","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Annual Meeting of the Forum for Information Retrieval Evaluation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3574318.3574346","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3574318.3574346","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3574318.3574346","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Annual Meeting of the Forum for Information Retrieval Evaluation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4316192634.pdf","grobid_xml":"https://content.openalex.org/works/W4316192634.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W14754660","https://openalex.org/W1503259811","https://openalex.org/W1531522183","https://openalex.org/W1985514943","https://openalex.org/W1999302842","https://openalex.org/W2100368767","https://openalex.org/W2105330820","https://openalex.org/W2134913565","https://openalex.org/W2135413937","https://openalex.org/W2154462503","https://openalex.org/W2250539671","https://openalex.org/W2250612198","https://openalex.org/W2493916176","https://openalex.org/W2507731975","https://openalex.org/W2510998959","https://openalex.org/W2772276716","https://openalex.org/W2788009253","https://openalex.org/W2797938814","https://openalex.org/W2898914189","https://openalex.org/W2914163459","https://openalex.org/W2962739339","https://openalex.org/W2963421945","https://openalex.org/W2963477629","https://openalex.org/W2969068412","https://openalex.org/W2970343438","https://openalex.org/W3007062217","https://openalex.org/W3041864618","https://openalex.org/W3090378332","https://openalex.org/W3131324121","https://openalex.org/W4213009331"],"related_works":["https://openalex.org/W2946409105","https://openalex.org/W3152932816","https://openalex.org/W2985392712","https://openalex.org/W4388996947","https://openalex.org/W3133567596","https://openalex.org/W2798009317","https://openalex.org/W4382201653","https://openalex.org/W3203949288","https://openalex.org/W3175524270","https://openalex.org/W2998070955"],"abstract_inverted_index":{"While":[0],"a":[1,60,83,123,126],"class":[2],"of":[3,15,32,36,43,78,89,100,111,122,128,136],"data-driven":[4],"approaches":[5,67,140],"has":[6],"been":[7],"shown":[8],"to":[9,95],"be":[10],"effective":[11],"in":[12],"embedding":[13,45,49,131],"words":[14,104],"languages":[16],"that":[17,77,117],"are":[18],"relatively":[19],"simple":[20],"as":[21,52,125],"per":[22],"inflections":[23],"and":[24,145],"compounding":[25,120],"characteristics":[26,39],"(e.g.":[27],"English),":[28],"an":[29,44],"open":[30],"area":[31],"investigation":[33],"is":[34],"ways":[35],"integrating":[37],"language-specific":[38],"within":[40],"the":[41,72,90,98,101,109,119,129],"framework":[42],"model.":[46],"Standard":[47],"word":[48,58,79,85,130,142,146],"approaches,":[50],"such":[51],"word2vec,":[53],"Glove":[54],"etc.":[55],"embed":[56],"each":[57],"into":[59],"high":[61],"dimensional":[62],"dense":[63],"vector.":[64],"However,":[65],"these":[66],"may":[68],"not":[69],"adequately":[70],"capture":[71],"inherent":[73],"linguistic":[74],"phenomenon":[75],"namely":[76],"compounding.":[80],"We":[81],"propose":[82],"stochastic":[84],"transformation":[86],"based":[87,139],"generalization":[88],"skip-gram":[91],"algorithm,":[92],"which":[93],"seeks":[94],"potentially":[96],"improve":[97],"representation":[99],"compositional":[102],"compound":[103],"by":[105],"leveraging":[106],"information":[107],"from":[108],"contexts":[110],"their":[112],"constituents.":[113],"Our":[114],"experiments":[115],"show":[116],"addressing":[118],"effect":[121],"language":[124],"part":[127],"objective":[132],"outperforms":[133],"existing":[134],"methods":[135],"compounding-specific":[137],"post-transformation":[138],"on":[141],"semantics":[143],"prediction":[144,148],"polarity":[147],"tasks.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}