{"id":"https://openalex.org/W3174449720","doi":"https://doi.org/10.1609/aaai.v35i15.17611","title":"Data Augmentation for Abstractive Query-Focused Multi-Document Summarization","display_name":"Data Augmentation for Abstractive Query-Focused Multi-Document Summarization","publication_year":2021,"publication_date":"2021-05-18","ids":{"openalex":"https://openalex.org/W3174449720","doi":"https://doi.org/10.1609/aaai.v35i15.17611","mag":"3174449720"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v35i15.17611","doi":"https://doi.org/10.1609/aaai.v35i15.17611","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i15.17611","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v35i15.17611","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075564427","display_name":"Ramakanth Pasunuru","orcid":null,"observed_orcids":[]},"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":"Ramakanth Pasunuru","raw_affiliation_strings":["University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030468199","display_name":"Asl\u0131 \u00c7eliky\u0131lmaz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asli Celikyilmaz","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107838508","display_name":"Michel Galley","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michel Galley","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102363883","display_name":"Chenyan Xiong","orcid":"https://orcid.org/0000-0002-0392-4183","observed_orcids":["https://orcid.org/0000-0002-0392-4183"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenyan Xiong","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101959000","display_name":"Yizhe Zhang","orcid":"https://orcid.org/0000-0002-9599-7995","observed_orcids":["https://orcid.org/0000-0002-9599-7995"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yizhe Zhang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001987532","display_name":"Mohit Bansal","orcid":"https://orcid.org/0000-0001-5522-1351","observed_orcids":["https://orcid.org/0000-0001-5522-1351"]},"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":"Mohit Bansal","raw_affiliation_strings":["University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143","observed_orcids":["https://orcid.org/0000-0002-5702-6143"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4572,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.9427615,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"35","issue":"15","first_page":"13666","last_page":"13674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6435999870300293,"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":0.6435999870300293,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.2824999988079071,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.03689999878406525,"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/abstractive-summarization","display_name":"abstractive summarization","score":0.8960000276565552},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.9739999771118164},{"id":"https://openalex.org/keywords/training-dataset-construction","display_name":"training dataset construction","score":0.875},{"id":"https://openalex.org/keywords/search-query-logs","display_name":"search query logs","score":0.722000002861023},{"id":"https://openalex.org/keywords/hierarchical-encoder","display_name":"hierarchical encoder","score":0.8080000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8784711360931396},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8632432818412781},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5989299416542053},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5061299204826355},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45427900552749634},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.45421019196510315},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.45000576972961426},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4414089322090149},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43407657742500305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29893970489501953},{"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v35i15.17611","doi":"https://doi.org/10.1609/aaai.v35i15.17611","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i15.17611","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2103.01863","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.01863","pdf_url":"https://arxiv.org/pdf/2103.01863","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,"listed_in":[],"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":"pmh:oai:ojs.aaai.org:article/17611","doi":null,"is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/17611","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/17611/17418","source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2103.01863","doi":"https://doi.org/10.48550/arxiv.2103.01863","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.01863","pdf_url":null,"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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v35i15.17611","doi":"https://doi.org/10.1609/aaai.v35i15.17611","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i15.17611","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G572880119","display_name":"CAREER: Semantic Multi-Task Learning for Generalizable and Interpretable Language Generation","funder_award_id":"1846185","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174449720.pdf","grobid_xml":"https://content.openalex.org/works/W3174449720.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1497212108","https://openalex.org/W1544827683","https://openalex.org/W1677182931","https://openalex.org/W1843891098","https://openalex.org/W1939882552","https://openalex.org/W1975579663","https://openalex.org/W1994118833","https://openalex.org/W1995945562","https://openalex.org/W2016522586","https://openalex.org/W2051618067","https://openalex.org/W2083305840","https://openalex.org/W2102865756","https://openalex.org/W2103339462","https://openalex.org/W2110693578","https://openalex.org/W2118733980","https://openalex.org/W2128672521","https://openalex.org/W2148374900","https://openalex.org/W2154652894","https://openalex.org/W2158751803","https://openalex.org/W2160992478","https://openalex.org/W2293778248","https://openalex.org/W2307381258","https://openalex.org/W2467173223","https://openalex.org/W2525778437","https://openalex.org/W2579653291","https://openalex.org/W2597655663","https://openalex.org/W2606974598","https://openalex.org/W2626778328","https://openalex.org/W2742009068","https://openalex.org/W2785076661","https://openalex.org/W2787214294","https://openalex.org/W2788283780","https://openalex.org/W2794945088","https://openalex.org/W2796084947","https://openalex.org/W2797563284","https://openalex.org/W2798990753","https://openalex.org/W2799064010","https://openalex.org/W2885185669","https://openalex.org/W2889518897","https://openalex.org/W2902706465","https://openalex.org/W2948120406","https://openalex.org/W2950670227","https://openalex.org/W2962946054","https://openalex.org/W2962972512","https://openalex.org/W2962985882","https://openalex.org/W2963929190","https://openalex.org/W3012754796","https://openalex.org/W3027372696","https://openalex.org/W3138773240","https://openalex.org/W4251326898","https://openalex.org/W6683252230","https://openalex.org/W7096849223"],"related_works":["https://openalex.org/W2975721763","https://openalex.org/W3094041811","https://openalex.org/W3197149826","https://openalex.org/W2902706465","https://openalex.org/W4225958595","https://openalex.org/W2799044970","https://openalex.org/W2988089622","https://openalex.org/W4393161143","https://openalex.org/W3138786034","https://openalex.org/W3096783161"],"abstract_inverted_index":{"The":[0],"progress":[1],"in":[2],"Query-focused":[3],"Multi-Document":[4],"Summarization":[5],"(QMDS)":[6],"has":[7,66,75],"been":[8],"limited":[9],"by":[10],"the":[11,35,45,55,98,123],"lack":[12],"of":[13,122],"sufficient":[14],"largescale":[15],"high-quality":[16],"training":[17,23],"datasets.":[18,109],"We":[19,110],"present":[20],"two":[21,29,59],"QMDS":[22],"datasets,":[24],"which":[25],"we":[26,90],"construct":[27],"using":[28],"data":[30,134],"augmentation":[31,135],"methods:":[32],"(1)":[33],"transferring":[34],"commonly":[36],"used":[37],"single-document":[38],"CNN/Daily":[39],"Mail":[40],"summarization":[41],"dataset":[42],"to":[43,53],"create":[44,54],"QMDSCNN":[46,65],"dataset,":[47],"and":[48,87,136],"(2)":[49],"mining":[50],"search-query":[51],"logs":[52],"QMDSIR":[56,74],"dataset.":[57],"These":[58],"datasets":[60,100],"have":[61],"complementary":[62],"properties,":[63],"i.e.,":[64],"real":[67,76,85],"summaries":[68],"but":[69,78],"queries":[70,77],"are":[71],"simulated,":[72],"while":[73],"simulated":[79],"summaries.":[80],"To":[81],"cover":[82],"both":[83],"these":[84],"summary":[86],"query":[88,124],"aspects,":[89],"build":[91],"abstractive":[92],"end-to-end":[93],"neural":[94],"network":[95],"models":[96,141],"on":[97,107,142,148],"combined":[99],"that":[101,116,132],"yield":[102],"new":[103,113],"state-of-the-art":[104],"transfer":[105],"results":[106,130],"DUC":[108],"also":[111],"introduce":[112],"hierarchical":[114],"encoders":[115],"enable":[117],"a":[118],"more":[119],"efficient":[120],"encoding":[121,137],"together":[125],"with":[126],"multiple":[127,152],"documents.":[128],"Empirical":[129],"demonstrate":[131],"our":[133],"methods":[138],"outperform":[139],"baseline":[140],"automatic":[143],"metrics,":[144],"as":[145,147],"well":[146],"human":[149],"evaluations":[150],"along":[151],"attributes.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-07-05T00:00:00"}