{"id":"https://openalex.org/W3012639927","doi":"https://doi.org/10.1145/3366423.3380060","title":"Distant Supervision for Multi-Stage Fine-Tuning in Retrieval-Based Question Answering","display_name":"Distant Supervision for Multi-Stage Fine-Tuning in Retrieval-Based Question Answering","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3012639927","doi":"https://doi.org/10.1145/3366423.3380060","mag":"3012639927"},"language":"en","primary_location":{"id":"doi:10.1145/3366423.3380060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380060","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 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3366423.3380060","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019841406","display_name":"Yuqing Xie","orcid":"https://orcid.org/0000-0001-9693-4892"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Yuqing Xie","raw_affiliation_strings":["University of Waterloo"],"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101866601","display_name":"Wei Yang","orcid":"https://orcid.org/0000-0003-1266-048X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Yang","raw_affiliation_strings":["RSVP.ai"],"affiliations":[{"raw_affiliation_string":"RSVP.ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043679408","display_name":"Luchen Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luchen Tan","raw_affiliation_strings":["RSVP.ai"],"affiliations":[{"raw_affiliation_string":"RSVP.ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023824766","display_name":"Kun Xiong","orcid":"https://orcid.org/0000-0003-1431-6586"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Xiong","raw_affiliation_strings":["RSVP.ai"],"affiliations":[{"raw_affiliation_string":"RSVP.ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053345000","display_name":"Nicholas Jing Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicholas Jing Yuan","raw_affiliation_strings":["HUAWEI Cloud & AI"],"affiliations":[{"raw_affiliation_string":"HUAWEI Cloud & AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020858666","display_name":"Baoxing Huai","orcid":"https://orcid.org/0000-0001-9625-2314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baoxing Huai","raw_affiliation_strings":["HUAWEI Cloud & AI"],"affiliations":[{"raw_affiliation_string":"HUAWEI Cloud & AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351398","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-2157-2775"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["University of Waterloo"],"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Waterloo"],"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5019841406"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":2.3861,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.9072584,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2934","last_page":"2940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T13274","display_name":"Expert finding and Q&A systems","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9807999730110168,"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/computer-science","display_name":"Computer science","score":0.6850084066390991},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6404561996459961},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.5865919589996338},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48942437767982483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3633313775062561}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6850084066390991},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6404561996459961},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.5865919589996338},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48942437767982483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3633313775062561},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3366423.3380060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380060","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 2020","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3366423.3380060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380060","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 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1631063262","https://openalex.org/W2101210369","https://openalex.org/W2251818205","https://openalex.org/W2740321901","https://openalex.org/W2799081691","https://openalex.org/W2799915114","https://openalex.org/W2889729765","https://openalex.org/W2899154813","https://openalex.org/W2949803292","https://openalex.org/W2949847757","https://openalex.org/W2950729111","https://openalex.org/W2951434086","https://openalex.org/W2962739339","https://openalex.org/W2962865973","https://openalex.org/W2962985038","https://openalex.org/W2963159735","https://openalex.org/W2963339397","https://openalex.org/W2963748441"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912"],"abstract_inverted_index":{"We":[0,66,127],"tackle":[1],"the":[2,29,82,90,109,136,139,149],"problem":[3],"of":[4,16,31,70,85,138],"question":[5],"answering":[6],"directly":[7],"on":[8,119],"a":[9,21,36,68],"large":[10,115],"document":[11],"collection,":[12],"combining":[13],"simple":[14],"\u201cbag":[15],"words\u201d":[17],"passage":[18],"retrieval":[19],"with":[20,108],"BERT-based":[22],"reader":[23],"for":[24],"extracting":[25],"answer":[26],"spans.":[27],"In":[28],"context":[30],"this":[32,80],"architecture,":[33],"we":[34,112],"present":[35],"data":[37,153],"augmentation":[38],"technique":[39],"using":[40],"distant":[41],"supervision":[42],"to":[43,53,63,75,100,130],"automatically":[44],"annotate":[45],"paragraphs":[46],"as":[47],"either":[48],"positive":[49],"or":[50,134],"negative":[51,102],"examples":[52],"supplement":[54],"existing":[55],"training":[56],"data,":[57],"which":[58,145],"are":[59,73,128],"then":[60],"used":[61],"together":[62],"fine-tune":[64],"BERT.":[65],"explore":[67],"number":[69],"details":[71],"that":[72],"critical":[74],"achieving":[76],"high":[77],"accuracy":[78],"in":[79,117],"setup:":[81],"proper":[83],"sequencing":[84],"different":[86,98],"datasets":[87],"during":[88],"fine-tuning,":[89],"balance":[91],"between":[92],"\u201cdifficult\u201d":[93],"vs.":[94],"\u201ceasy\u201d":[95],"examples,":[96],"and":[97,122],"approaches":[99],"gathering":[101],"examples.":[103],"Experimental":[104],"results":[105,132],"show":[106],"that,":[107],"appropriate":[110],"settings,":[111],"can":[113],"achieve":[114,131],"gains":[116],"effectiveness":[118],"two":[120,123],"English":[121],"Chinese":[124],"QA":[125],"datasets.":[126],"able":[129],"at":[133],"near":[135],"state":[137],"art":[140],"without":[141],"any":[142],"modeling":[143],"advances,":[144],"once":[146],"again":[147],"affirms":[148],"clich\u00e9":[150],"\u201cthere\u2019s":[151],"no":[152],"like":[154],"more":[155],"data\u201d.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}