{"id":"https://openalex.org/W3019155698","doi":"https://doi.org/10.1017/s1351324920000194","title":"Is your document novel? Let attention guide you. An attention-based model for document-level novelty detection","display_name":"Is your document novel? Let attention guide you. An attention-based model for document-level novelty detection","publication_year":2020,"publication_date":"2020-04-24","ids":{"openalex":"https://openalex.org/W3019155698","doi":"https://doi.org/10.1017/s1351324920000194","mag":"3019155698"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324920000194","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324920000194","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5081072666","display_name":"Tirthankar Ghosal","orcid":"https://orcid.org/0000-0002-2358-522X"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Tirthankar Ghosal","raw_affiliation_strings":["Indian Institute of Technology Patna, Bihta, Bihar, Patna801103, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Bihta, Bihar, Patna801103, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040201460","display_name":"Vignesh Edithal","orcid":null},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vignesh Edithal","raw_affiliation_strings":["Indian Institute of Technology Patna, Bihta, Bihar, Patna801103, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Bihta, Bihar, Patna801103, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085370631","display_name":"Asif Ekbal","orcid":"https://orcid.org/0000-0003-3612-8834"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Asif Ekbal","raw_affiliation_strings":["Indian Institute of Technology Patna, Bihta, Bihar, Patna801103, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Bihta, Bihar, Patna801103, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065100828","display_name":"Pushpak Bhattacharyya","orcid":"https://orcid.org/0000-0001-5319-5508"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pushpak Bhattacharyya","raw_affiliation_strings":["Indian Institute of Technology Patna, Bihta, Bihar, Patna801103, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Bihta, Bihar, Patna801103, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084296557","display_name":"Srinivasa Satya Sameer Kumar Chivukula","orcid":null},"institutions":[{"id":"https://openalex.org/I1318003438","display_name":"RELX Group (Netherlands)","ror":"https://ror.org/02scfj030","country_code":"NL","type":"company","lineage":["https://openalex.org/I1318003438","https://openalex.org/I4210160603"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Srinivasa Satya Sameer Kumar Chivukula","raw_affiliation_strings":["Elsevier, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Elsevier, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1318003438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080654893","display_name":"George Tsatsaronis","orcid":"https://orcid.org/0000-0003-2116-2933"},"institutions":[{"id":"https://openalex.org/I1318003438","display_name":"RELX Group (Netherlands)","ror":"https://ror.org/02scfj030","country_code":"NL","type":"company","lineage":["https://openalex.org/I1318003438","https://openalex.org/I4210160603"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"George Tsatsaronis","raw_affiliation_strings":["Elsevier, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Elsevier, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1318003438"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5081072666"],"corresponding_institution_ids":["https://openalex.org/I132153292"],"apc_list":null,"apc_paid":null,"fwci":0.68,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.7611976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"27","issue":"4","first_page":"427","last_page":"454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.9987000226974487,"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/T10260","display_name":"Software Engineering Research","score":0.9962999820709229,"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/T11719","display_name":"Data Quality and Management","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8782204389572144},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.8231070041656494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7088075280189514},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"Novelty detection","score":0.6497149467468262},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5818999409675598},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5802356600761414},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5698802471160889},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5024924278259277},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49837255477905273},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4783344268798828},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.4496869146823883},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33540254831314087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3310287296772003},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.25418001413345337}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8782204389572144},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.8231070041656494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7088075280189514},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.6497149467468262},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5818999409675598},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5802356600761414},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5698802471160889},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5024924278259277},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49837255477905273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4783344268798828},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.4496869146823883},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33540254831314087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3310287296772003},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25418001413345337},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324920000194","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324920000194","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W53209706","https://openalex.org/W63837240","https://openalex.org/W73694622","https://openalex.org/W1230283387","https://openalex.org/W1481997832","https://openalex.org/W1542258417","https://openalex.org/W1556151859","https://openalex.org/W1631885887","https://openalex.org/W1840435438","https://openalex.org/W1964793108","https://openalex.org/W1965160072","https://openalex.org/W1975879668","https://openalex.org/W1981825277","https://openalex.org/W1983811220","https://openalex.org/W1988107199","https://openalex.org/W1998224037","https://openalex.org/W2005449026","https://openalex.org/W2007760849","https://openalex.org/W2014235936","https://openalex.org/W2015287556","https://openalex.org/W2026430213","https://openalex.org/W2046166484","https://openalex.org/W2053959297","https://openalex.org/W2054090049","https://openalex.org/W2055294489","https://openalex.org/W2056664748","https://openalex.org/W2072284402","https://openalex.org/W2080527295","https://openalex.org/W2081798681","https://openalex.org/W2086925418","https://openalex.org/W2091362531","https://openalex.org/W2092464680","https://openalex.org/W2096623622","https://openalex.org/W2120401584","https://openalex.org/W2131744502","https://openalex.org/W2132314908","https://openalex.org/W2133564696","https://openalex.org/W2154573757","https://openalex.org/W2161396019","https://openalex.org/W2250385510","https://openalex.org/W2275485090","https://openalex.org/W2340802269","https://openalex.org/W2396767181","https://openalex.org/W2413794162","https://openalex.org/W2415204069","https://openalex.org/W2520855119","https://openalex.org/W2576792795","https://openalex.org/W2752172973","https://openalex.org/W2763722198","https://openalex.org/W2788767996","https://openalex.org/W2878470635","https://openalex.org/W2891177506","https://openalex.org/W2949547296","https://openalex.org/W2963918774","https://openalex.org/W3138773240","https://openalex.org/W4211148418","https://openalex.org/W4234917632","https://openalex.org/W4242539510","https://openalex.org/W4285719527","https://openalex.org/W6600976540","https://openalex.org/W6602621892","https://openalex.org/W6628747921","https://openalex.org/W6745573522"],"related_works":["https://openalex.org/W2064636555","https://openalex.org/W2585503716","https://openalex.org/W1939982668","https://openalex.org/W2105014086","https://openalex.org/W2076090200","https://openalex.org/W4312933423","https://openalex.org/W3025682415","https://openalex.org/W1532481220","https://openalex.org/W2081173909","https://openalex.org/W4382317424"],"abstract_inverted_index":{"Abstract":[0],"Detecting,":[1],"whether":[2],"a":[3,57,106,117,148],"document":[4],"contains":[5],"sufficient":[6],"new":[7],"information":[8],"to":[9,40,76,126],"be":[10],"deemed":[11],"as":[12],"novel":[13],",":[14],"is":[15,133],"of":[16,22,91,103,105,150,155],"immense":[17],"significance":[18],"in":[19,56,153],"this":[20],"age":[21],"data":[23],"duplication.":[24],"Existing":[25],"techniques":[26,46],"for":[27],"document-level":[28,78,144],"novelty":[29,79,104,128,145],"detection":[30,129,146],"mostly":[31],"perform":[32],"at":[33],"the":[34,42,54,88,94,101,127,137],"lexical":[35],"level":[36],"and":[37,96,135,140],"are":[38],"unable":[39],"address":[41],"semantic-level":[43],"redundancy.":[44],"These":[45],"usually":[47],"rely":[48],"on":[49,72,143],"handcrafted":[50],"features":[51],"extracted":[52],"from":[53,116],"documents":[55],"rule-based":[58],"or":[59],"traditional":[60],"feature-based":[61],"machine":[62],"learning":[63],"setup.":[64],"Here,":[65],"we":[66],"present":[67],"an":[68],"effective":[69,134],"approach":[70,132],"based":[71],"neural":[73,111],"attention":[74],"mechanism":[75],"detect":[77],"without":[80],"any":[81],"manual":[82],"feature":[83],"engineering.":[84],"We":[85],"contend":[86],"that":[87],"simple":[89],"alignment":[90],"texts":[92],"between":[93],"source":[95],"target":[97,107],"document(s)":[98],"could":[99],"identify":[100],"state":[102],"document.":[108],"Our":[109,131],"deep":[110],"architecture":[112],"elicits":[113],"inference":[114,121],"knowledge":[115],"large-scale":[118],"natural":[119],"language":[120],"dataset,":[122],"which":[123],"proves":[124],"crucial":[125],"task.":[130],"outperforms":[136],"standard":[138],"baselines":[139],"recent":[141],"work":[142],"by":[147],"margin":[149],"$\\sim$":[151],"3%":[152],"terms":[154],"accuracy.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}