{"id":"https://openalex.org/W2948980849","doi":"https://doi.org/10.18653/v1/p19-1168","title":"Topic Sensitive Attention on Generic Corpora Corrects Sense Bias in Pretrained Embeddings","display_name":"Topic Sensitive Attention on Generic Corpora Corrects Sense Bias in Pretrained Embeddings","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2948980849","doi":"https://doi.org/10.18653/v1/p19-1168","mag":"2948980849"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1168","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1168","pdf_url":"https://www.aclweb.org/anthology/P19-1168.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1168.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079415699","display_name":"Vihari Piratla","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Vihari Piratla","raw_affiliation_strings":["Indian Institute of Technology Bombay"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031035935","display_name":"Sunita Sarawagi","orcid":"https://orcid.org/0009-0005-9538-6616"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunita Sarawagi","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457009","display_name":"Soumen Chakrabarti","orcid":"https://orcid.org/0000-0002-9419-7486"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soumen Chakrabarti","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079415699"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.1447,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56365785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1717","last_page":"1726"},"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":0.9976000189781189,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9962000250816345,"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/regularization","display_name":"Regularization (linguistics)","score":0.7991840839385986},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7189070582389832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7094048261642456},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6469911932945251},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5488000512123108},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5090720057487488},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5024383068084717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4923743009567261},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4768039882183075},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3242819905281067},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16592633724212646}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7991840839385986},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7189070582389832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7094048261642456},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6469911932945251},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5488000512123108},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5090720057487488},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5024383068084717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4923743009567261},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4768039882183075},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3242819905281067},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16592633724212646},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p19-1168","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1168","pdf_url":"https://www.aclweb.org/anthology/P19-1168.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.02688","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.02688","pdf_url":"https://arxiv.org/pdf/1906.02688","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2948980849","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.02688.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1906.02688","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.02688","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1168","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1168","pdf_url":"https://www.aclweb.org/anthology/P19-1168.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948980849.pdf","grobid_xml":"https://content.openalex.org/works/W2948980849.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1660390307","https://openalex.org/W2141671708","https://openalex.org/W2153579005","https://openalex.org/W2158108973","https://openalex.org/W2250539671","https://openalex.org/W2514776376","https://openalex.org/W2560647685","https://openalex.org/W2794557536","https://openalex.org/W2803777992","https://openalex.org/W2808127482","https://openalex.org/W2853138162","https://openalex.org/W2951815801","https://openalex.org/W2952113915","https://openalex.org/W2962739339","https://openalex.org/W2962802054","https://openalex.org/W2962887999","https://openalex.org/W2963026768","https://openalex.org/W2963087041","https://openalex.org/W2963090765","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963626623","https://openalex.org/W2963872035","https://openalex.org/W2964182988","https://openalex.org/W2964332570"],"related_works":["https://openalex.org/W2963293326","https://openalex.org/W3026043465","https://openalex.org/W2963850626","https://openalex.org/W2724648934","https://openalex.org/W2955348530","https://openalex.org/W2530085701","https://openalex.org/W2614551030","https://openalex.org/W2794132063","https://openalex.org/W2892354174","https://openalex.org/W2987819162","https://openalex.org/W3118556657","https://openalex.org/W2579644692","https://openalex.org/W2804398514","https://openalex.org/W3188030217","https://openalex.org/W2948607002","https://openalex.org/W2897994656","https://openalex.org/W2587764909","https://openalex.org/W2962883166","https://openalex.org/W2955515572","https://openalex.org/W2799060650"],"abstract_inverted_index":{"Given":[0],"a":[1,8,67,89,101,115,149],"small":[2,138],"corpus":[3,91,173,182,205],"D":[4,37,49,159],"T":[5,38,50,160],"pertaining":[6],"to":[7,17,60,161,184],"limited":[9,34,56,204],"set":[10],"of":[11,25,32,36,108,127],"focused":[12],"topics,":[13,120],"our":[14],"goal":[15],"is":[16,59,189,207],"train":[18],"embeddings":[19,41,63,225],"that":[20,130,202,215],"accurately":[21],"capture":[22],"the":[23,28,33,106,132,181,199],"sense":[24,73,217],"words":[26],"in":[27,30,45,55],"topic":[29],"spite":[31],"size":[35],".":[39,51],"These":[40],"may":[42,219],"be":[43,180,220,228],"used":[44,183],"various":[46],"tasks":[47],"involving":[48],"A":[52],"popular":[53],"strategy":[54],"data":[57],"settings":[58,126],"adapt":[61],"pretrained":[62,154,224],"E":[64],"trained":[65],"on":[66,105],"large":[68],"corpus.":[69],"To":[70],"correct":[71],"for":[72],"drift,":[74],"fine-tuning,":[75],"regularization,":[76],"projection,":[77],"and":[78,165,192,226],"pivoting":[79],"have":[80],"been":[81],"proposed":[82],"recently.":[83],"Among":[84],"these,":[85],"regularization":[86],"informed":[87],"by":[88,194,230],"word's":[90],"frequency":[92],"performed":[93],"well,":[94],"but":[95],"we":[96,156],"improve":[97],"upon":[98],"it":[99],"using":[100,158],"new":[102],"regularizer":[103],"based":[104],"stability":[107],"its":[109],"cooccurrence":[110],"with":[111,124],"other":[112],"words.":[113],"However,":[114],"thorough":[116],"comparison":[117],"across":[118],"ten":[119],"spanning":[121],"three":[122],"tasks,":[123],"standardized":[125],"hyper-parameters,":[128],"reveals":[129],"even":[131,203],"best":[133],"embedding":[134],"adaptation":[135],"strategies":[136],"provide":[137],"gains":[139],"beyond":[140],"well-tuned":[141],"baselines,":[142],"which":[143,177,213],"many":[144],"earlier":[145],"comparisons":[146],"ignored.":[147],"In":[148],"bold":[150],"departure":[151],"from":[152,168,223],"adapting":[153,211],"embeddings,":[155,212],"propose":[157],"probe,":[162],"attend":[163],"to,":[164],"borrow":[166],"fragments":[167],"any":[169],"large,":[170],"topic-rich":[171],"source":[172],"(such":[174],"as":[175],"Wikipedia),":[176],"need":[178],"not":[179],"pretrain":[185],"embeddings.":[186],"This":[187],"step":[188],"made":[190],"scalable":[191],"practical":[193],"suitable":[195],"indexing.":[196],"We":[197],"reach":[198],"surprising":[200],"conclusion":[201],"augmentation":[206],"more":[208],"useful":[209],"than":[210],"suggests":[214],"non-dominant":[216],"information":[218],"irrevocably":[221],"obliterated":[222],"cannot":[227],"salvaged":[229],"adaptation.":[231]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-07-29T00:00:00"}