{"id":"https://openalex.org/W3198384869","doi":"https://doi.org/10.1109/tnnls.2021.3107029","title":"MGRC: An End-to-End Multigranularity Reading Comprehension Model for Question Answering","display_name":"MGRC: An End-to-End Multigranularity Reading Comprehension Model for Question Answering","publication_year":2021,"publication_date":"2021-09-03","ids":{"openalex":"https://openalex.org/W3198384869","doi":"https://doi.org/10.1109/tnnls.2021.3107029","mag":"3198384869","pmid":"https://pubmed.ncbi.nlm.nih.gov/34478387"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3107029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3107029","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037327117","display_name":"Qian Liu","orcid":"https://orcid.org/0000-0002-3162-935X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]},{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Qian Liu","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, NSW, Australia","School of Computer Science, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"School of Computer Science, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084564357","display_name":"Xiubo Geng","orcid":"https://orcid.org/0000-0001-6477-7933"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiubo Geng","raw_affiliation_strings":["STCA-NLP Group, Microsoft Company, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6477-7933","affiliations":[{"raw_affiliation_string":"STCA-NLP Group, Microsoft Company, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087631670","display_name":"Heyan Huang","orcid":"https://orcid.org/0000-0002-0320-7520"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heyan Huang","raw_affiliation_strings":["School of Computer Science, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0320-7520","affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020025718","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0002-9095-0776"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":["STCA-NLP Group, Microsoft Company, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9095-0776","affiliations":[{"raw_affiliation_string":"STCA-NLP Group, Microsoft Company, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675577","display_name":"Jie L\u00fc","orcid":"https://orcid.org/0000-0003-0690-4732"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jie Lu","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0690-4732","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060116992","display_name":"Daxin Jiang","orcid":"https://orcid.org/0000-0002-6657-5806"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daxin Jiang","raw_affiliation_strings":["STCA-NLP Group, Microsoft Company, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STCA-NLP Group, Microsoft Company, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1837,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.89632198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"34","issue":"5","first_page":"2594","last_page":"2605"},"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9668999910354614,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8580865859985352},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7327502369880676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6611092686653137},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6610746383666992},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.6346507668495178},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5612695217132568},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5481005311012268},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5281757712364197},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.49069344997406006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48457300662994385},{"id":"https://openalex.org/keywords/reading-comprehension","display_name":"Reading comprehension","score":0.47075703740119934},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4357568323612213},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42984744906425476},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4241890609264374},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4144717752933502},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.36208081245422363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8580865859985352},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7327502369880676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6611092686653137},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6610746383666992},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.6346507668495178},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5612695217132568},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5481005311012268},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5281757712364197},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.49069344997406006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48457300662994385},{"id":"https://openalex.org/C2778780117","wikidata":"https://www.wikidata.org/wiki/Q3269423","display_name":"Reading comprehension","level":3,"score":0.47075703740119934},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4357568323612213},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42984744906425476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4241890609264374},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4144717752933502},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.36208081245422363},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3107029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3107029","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34478387","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34478387","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7920740482","display_name":null,"funder_award_id":"U19B2020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1875842236","https://openalex.org/W2516930406","https://openalex.org/W2551396370","https://openalex.org/W2557764419","https://openalex.org/W2600024417","https://openalex.org/W2606964149","https://openalex.org/W2741263286","https://openalex.org/W2770970123","https://openalex.org/W2785176118","https://openalex.org/W2788448041","https://openalex.org/W2798586382","https://openalex.org/W2799081691","https://openalex.org/W2896457183","https://openalex.org/W2907822478","https://openalex.org/W2912924812","https://openalex.org/W2949210751","https://openalex.org/W2949428332","https://openalex.org/W2949615363","https://openalex.org/W2949847757","https://openalex.org/W2951534261","https://openalex.org/W2962739339","https://openalex.org/W2962985038","https://openalex.org/W2963159735","https://openalex.org/W2963350559","https://openalex.org/W2963748441","https://openalex.org/W2963969878","https://openalex.org/W2965373594","https://openalex.org/W2970139579","https://openalex.org/W2970597249","https://openalex.org/W2970723181","https://openalex.org/W3034364750","https://openalex.org/W3098057198","https://openalex.org/W3098672388","https://openalex.org/W4288623406","https://openalex.org/W4300928827","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6632455782","https://openalex.org/W6726253136","https://openalex.org/W6729654139","https://openalex.org/W6729938257","https://openalex.org/W6735889696","https://openalex.org/W6739901393","https://openalex.org/W6745884811","https://openalex.org/W6746261267","https://openalex.org/W6749101747","https://openalex.org/W6754865795","https://openalex.org/W6755207826","https://openalex.org/W6757721448","https://openalex.org/W6758274703","https://openalex.org/W6760019105","https://openalex.org/W6763701032","https://openalex.org/W6766673545"],"related_works":["https://openalex.org/W2377059580","https://openalex.org/W4200355488","https://openalex.org/W2391800119","https://openalex.org/W2052919063","https://openalex.org/W2595239241","https://openalex.org/W2799181378","https://openalex.org/W3003711649","https://openalex.org/W2904173691","https://openalex.org/W4365517254","https://openalex.org/W270947280"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network-based":[2],"models":[3],"have":[4,15],"achieved":[5],"great":[6],"success":[7],"in":[8,144,155,215],"extractive":[9],"question":[10],"answering.":[11],"Recently,":[12],"many":[13],"works":[14],"been":[16],"proposed":[17,188,213],"to":[18,62,67,115],"model":[19,117,158,195,217],"multistage":[20,95,198],"matching":[21,119,166,199],"for":[22,55],"this":[23],"task,":[24],"which":[25,110],"usually":[26,60],"first":[27],"retrieve":[28],"relevant":[29],"paragraphs":[30],"or":[31],"sentences":[32],"and":[33,78,126,148,181,184,196,207],"then":[34],"extract":[35],"an":[36,204],"answer":[37,80,127],"span":[38],"from":[39,49],"the":[40,50,68,75,79,92,136,140,146,152,160,187,192,209,212],"retrieved":[41],"results.":[42],"However,":[43],"such":[44],"a":[45,103,112,156,170],"pipeline-based":[46],"approach":[47,130,138,189],"suffers":[48],"error":[51,141],"propagation":[52,142],"problem,":[53],"especially":[54],"sentence-level":[56],"retrieval":[57],"that":[58,186],"is":[59,111],"difficult":[61],"achieve":[63],"high":[64],"accuracy":[65],"due":[66],"severe":[69],"data":[70],"imbalance":[71],"problem.":[72],"Furthermore,":[73],"since":[74],"paragraph/sentence":[76],"selector":[77],"extractor":[81],"are":[82],"closely":[83],"related,":[84],"modeling":[85],"them":[86],"independently":[87],"does":[88],"not":[89],"fully":[90],"exploit":[91],"power":[93],"of":[94,162,164,211],"matching.":[96],"To":[97],"solve":[98],"these":[99],"problems,":[100],"we":[101],"propose":[102],"novel":[104],"end-to-end":[105,137],"multigranularity":[106],"reading":[107],"comprehension":[108],"model,":[109],"unified":[113,157],"framework":[114],"explicitly":[116],"three":[118],"granularities,":[120],"including":[121],"paragraph":[122],"identification,":[123],"sentence":[124],"selection,":[125],"extraction.":[128],"Our":[129],"has":[131],"two":[132],"main":[133],"advantages.":[134],"First,":[135],"alleviates":[139],"problem":[143],"both":[145,191],"training":[147],"inference":[149],"phases.":[150],"Second,":[151],"shared":[153],"features":[154],"improve":[159],"learning":[161],"representations":[163],"different":[165],"granularities.":[167],"We":[168,201],"conduct":[169,203],"comprehensive":[171],"comparison":[172],"on":[173],"four":[174],"large-scale":[175],"datasets":[176],"(SQuAD-open,":[177],"NewsQA,":[178],"SQuAD":[179,182],"2.0,":[180],"Adversarial)":[183],"verify":[185,208],"outperforms":[190],"vanilla":[193],"BERT":[194],"existing":[197],"approaches.":[200],"also":[202],"ablation":[205],"study":[206],"effectiveness":[210],"components":[214],"our":[216],"structure.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}