{"id":"https://openalex.org/W3130347092","doi":"https://doi.org/10.1145/3442381.3449988","title":"Using Prior Knowledge to Guide BERT\u2019s Attention in Semantic Textual Matching Tasks","display_name":"Using Prior Knowledge to Guide BERT\u2019s Attention in Semantic Textual Matching Tasks","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3130347092","doi":"https://doi.org/10.1145/3442381.3449988","mag":"3130347092"},"language":"en","primary_location":{"id":"doi:10.1145/3442381.3449988","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449988","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 Web Conference 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3442381.3449988","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083820813","display_name":"Tingyu Xia","orcid":"https://orcid.org/0000-0002-4785-9969"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingyu Xia","raw_affiliation_strings":["School of Artificial Intelligence and Jilin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Jilin University, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371984","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0002-0278-2347"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["School of Information and Library Science and University of North Carolina at Chapel Hill, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Library Science and University of North Carolina at Chapel Hill, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716461","display_name":"Yuan Tian","orcid":"https://orcid.org/0000-0003-1242-6714"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Tian","raw_affiliation_strings":["School of Artificial Intelligence and Jilin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Jilin University, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029392006","display_name":"Yi Chang","orcid":"https://orcid.org/0000-0003-2697-8093"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Chang","raw_affiliation_strings":["School of Artificial Intelligence and Jilin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Jilin University, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2466","last_page":"2475"},"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":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8657790422439575},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7117268443107605},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5935402512550354},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5657521486282349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.54954594373703},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5375997424125671},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.46859899163246155},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4520225524902344},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4317694902420044},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3359067440032959}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8657790422439575},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7117268443107605},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5935402512550354},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5657521486282349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.54954594373703},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5375997424125671},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.46859899163246155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4520225524902344},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4317694902420044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3359067440032959},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3442381.3449988","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449988","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 Web Conference 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.10934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.10934","pdf_url":"https://arxiv.org/pdf/2102.10934","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"}],"best_oa_location":{"id":"doi:10.1145/3442381.3449988","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449988","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 Web Conference 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W2064675550","https://openalex.org/W2065249013","https://openalex.org/W2081580037","https://openalex.org/W2099884836","https://openalex.org/W2105946482","https://openalex.org/W2136480620","https://openalex.org/W2153702313","https://openalex.org/W2159583324","https://openalex.org/W2162130683","https://openalex.org/W2170738476","https://openalex.org/W2185606683","https://openalex.org/W2211192759","https://openalex.org/W2250539671","https://openalex.org/W2413794162","https://openalex.org/W2520305281","https://openalex.org/W2593833795","https://openalex.org/W2608787653","https://openalex.org/W2612867916","https://openalex.org/W2626778328","https://openalex.org/W2750779823","https://openalex.org/W2798416089","https://openalex.org/W2799054028","https://openalex.org/W2808633496","https://openalex.org/W2896457183","https://openalex.org/W2903064905","https://openalex.org/W2905233862","https://openalex.org/W2923014074","https://openalex.org/W2946359678","https://openalex.org/W2946417913","https://openalex.org/W2950813464","https://openalex.org/W2951359136","https://openalex.org/W2953025129","https://openalex.org/W2953356739","https://openalex.org/W2962369866","https://openalex.org/W2962739339","https://openalex.org/W2962753370","https://openalex.org/W2963341956","https://openalex.org/W2963508788","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2972324944","https://openalex.org/W2975059944","https://openalex.org/W2996428491","https://openalex.org/W2998230451","https://openalex.org/W2998385486","https://openalex.org/W3004346089","https://openalex.org/W3011411500","https://openalex.org/W3033187248","https://openalex.org/W3034238904","https://openalex.org/W3099023595","https://openalex.org/W3104033643","https://openalex.org/W3118485687","https://openalex.org/W3122890974","https://openalex.org/W4288351520","https://openalex.org/W4298210834","https://openalex.org/W4313908941","https://openalex.org/W4385245566","https://openalex.org/W4386506836"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2369710579","https://openalex.org/W4327728159","https://openalex.org/W4394266730","https://openalex.org/W1990856605","https://openalex.org/W2053783616","https://openalex.org/W2545348020","https://openalex.org/W2912751582"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,52,114,125,132,146,151],"problem":[3],"of":[4,46,75],"incorporating":[5],"prior":[6,77],"knowledge":[7,49,78,91],"into":[8,92],"a":[9,67,81,101],"deep":[10],"Transformer-based":[11],"model,":[12,149],"i.e.,":[13],"Bidirectional":[14],"Encoder":[15],"Representations":[16],"from":[17,116],"Transformers":[18],"(BERT),":[19],"to":[20,65,79,100,138],"enhance":[21],"its":[22],"performance":[23,144,152],"on":[24,118],"semantic":[25,141],"textual":[26,142],"matching":[27,143],"tasks.":[28],"By":[29],"probing":[30],"and":[31,54,150],"analyzing":[32],"what":[33,47],"BERT":[34,50,135,148],"has":[35],"already":[36],"known":[37],"when":[38,157],"solving":[39],"this":[40],"task,":[41],"we":[42,88],"obtain":[43],"better":[44],"understanding":[45],"task-specific":[48],"needs":[51],"most":[53,58,71,155],"where":[55],"it":[56,112],"is":[57,136,154,160],"needed.":[59],"The":[60],"analysis":[61],"further":[62],"motivates":[63],"us":[64,99],"take":[66],"different":[68],"approach":[69,105],"than":[70,124],"existing":[72],"works.":[73],"Instead":[74],"using":[76],"create":[80],"new":[82],"training":[83,109,117,158],"task":[84],"for":[85],"fine-tuning":[86],"BERT,":[87],"directly":[89],"inject":[90],"BERT\u2019s":[93],"multi-head":[94],"attention":[95],"mechanism.":[96],"This":[97],"leads":[98],"simple":[102],"yet":[103],"effective":[104],"that":[106,131],"enjoys":[107],"fast":[108],"stage":[110],"as":[111],"saves":[113],"model":[115],"additional":[119],"data":[120,159],"or":[121],"tasks":[122],"other":[123],"main":[126],"task.":[127],"Extensive":[128],"experiments":[129],"demonstrate":[130],"proposed":[133],"knowledge-enhanced":[134],"able":[137],"consistently":[139],"improve":[140],"over":[145],"original":[147],"benefit":[153],"salient":[156],"scarce.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}