{"id":"https://openalex.org/W2964609953","doi":"https://doi.org/10.24963/ijcai.2019/326","title":"Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation","display_name":"Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2964609953","doi":"https://doi.org/10.24963/ijcai.2019/326","mag":"2964609953"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/326","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/326","pdf_url":"https://www.ijcai.org/proceedings/2019/0326.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0326.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101518879","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-5429-6236"},"institutions":[{"id":"https://openalex.org/I184558857","display_name":"Royal Holloway University of London","ror":"https://ror.org/04g2vpn86","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I184558857"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yang Gao","raw_affiliation_strings":["Dept. of Computer Science, Royal Holloway, University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Royal Holloway, University of London","institution_ids":["https://openalex.org/I184558857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032750097","display_name":"Christian M. Meyer","orcid":"https://orcid.org/0000-0002-8673-7665"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian M. Meyer","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP-TUDA), Technische Universita \u0308t Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP-TUDA), Technische Universita \u0308t Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042169309","display_name":"Mohsen Mesgar","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mohsen Mesgar","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP-TUDA), Technische Universita \u0308t Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP-TUDA), Technische Universita \u0308t Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP-TUDA), Technische Universita \u0308t Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP-TUDA), Technische Universita \u0308t Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101518879"],"corresponding_institution_ids":["https://openalex.org/I184558857"],"apc_list":null,"apc_paid":null,"fwci":1.6943,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88288939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2350","last_page":"2356"},"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":0.9997000098228455,"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":0.9937999844551086,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.914839506149292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8403835296630859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6373983025550842},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6023688316345215},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5847494602203369},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.55907142162323},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.5240552425384521},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.1422467827796936},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06755098700523376}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.914839506149292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8403835296630859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6373983025550842},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6023688316345215},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5847494602203369},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.55907142162323},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.5240552425384521},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.1422467827796936},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06755098700523376},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/326","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/326","pdf_url":"https://www.ijcai.org/proceedings/2019/0326.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/326","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/326","pdf_url":"https://www.ijcai.org/proceedings/2019/0326.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G5741896422","display_name":null,"funder_award_id":"RI 803/12-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6215165406","display_name":null,"funder_award_id":"GU 798/18-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7805275943","display_name":null,"funder_award_id":"DA 1600/1-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8837226822","display_name":null,"funder_award_id":"GU 798/17-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964609953.pdf","grobid_xml":"https://content.openalex.org/works/W2964609953.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1527260130","https://openalex.org/W1832693441","https://openalex.org/W1999874108","https://openalex.org/W2075268401","https://openalex.org/W2101626488","https://openalex.org/W2145339207","https://openalex.org/W2150869743","https://openalex.org/W2154652894","https://openalex.org/W2155027007","https://openalex.org/W2170213349","https://openalex.org/W2176263492","https://openalex.org/W2251911042","https://openalex.org/W2559730228","https://openalex.org/W2790702239","https://openalex.org/W2797585226","https://openalex.org/W2800631850","https://openalex.org/W2804930149","https://openalex.org/W2886474253","https://openalex.org/W2896780650","https://openalex.org/W2962762898","https://openalex.org/W2962897543","https://openalex.org/W2962955856","https://openalex.org/W2962972512","https://openalex.org/W2963227052","https://openalex.org/W2963228265","https://openalex.org/W2964096423","https://openalex.org/W2964287878","https://openalex.org/W4230563027","https://openalex.org/W4289288058"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2772359885","https://openalex.org/W3011471740","https://openalex.org/W2954428433","https://openalex.org/W2884580467","https://openalex.org/W2572315477"],"abstract_inverted_index":{"Document":[0],"summarisation":[1,24],"can":[2,11],"be":[3,12],"formulated":[4],"as":[5],"a":[6,26,52,75,81],"sequential":[7],"decision-making":[8],"problem,":[9],"which":[10,29,63],"solved":[13],"by":[14,137],"Reinforcement":[15],"Learning":[16,47],"(RL)":[17],"algorithms.":[18,119],"The":[19],"predominant":[20],"RL":[21,49,77,100,118],"paradigm":[22,78],"for":[23],"learns":[25,80],"cross-input":[27],"policy,":[28],"requires":[30],"considerable":[31],"time,":[32],"data":[33],"and":[34,43,68,91,117],"parameter":[35],"tuning":[36],"due":[37],"to":[38,66,96,110,143],"the":[39,44,134,144],"huge":[40],"search":[41],"spaces":[42],"delayed":[45],"rewards.":[46],"input-specific":[48,99],"policies":[50],"is":[51],"more":[53],"efficient":[54],"alternative,":[55],"but":[56],"so":[57],"far":[58],"depends":[59],"on":[60,125,149],"handcrafted":[61],"rewards,":[62],"are":[64],"difficult":[65],"design":[67],"yield":[69],"poor":[70],"performance.":[71],"We":[72,105,129],"propose":[73],"RELIS,":[74],"novel":[76],"that":[79,107,131],"reward":[82,94],"function":[83,95],"with":[84,114,151],"Learning-to-Rank":[85],"(L2R)":[86],"algorithms":[87],"at":[88,102],"training":[89,135],"time":[90,136],"uses":[92],"this":[93],"train":[97],"an":[98],"policy":[101],"test":[103],"time.":[104],"prove":[106],"RELIS":[108,132],"guarantees":[109],"generate":[111],"near-optimal":[112],"summaries":[113],"appropriate":[115],"L2R":[116],"Empirically,":[120],"we":[121],"evaluate":[122],"our":[123],"approach":[124],"extractive":[126],"multi-document":[127],"summarisation.":[128],"show":[130],"reduces":[133],"two":[138],"orders":[139],"of":[140],"magnitude":[141],"compared":[142],"state-of-the-art":[145],"models":[146],"while":[147],"performing":[148],"par":[150],"them.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}