{"id":"https://openalex.org/W2799029897","doi":"https://doi.org/10.18653/v1/p18-1218","title":"Document Similarity for Texts of Varying Lengths via Hidden Topics","display_name":"Document Similarity for Texts of Varying Lengths via Hidden Topics","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2799029897","doi":"https://doi.org/10.18653/v1/p18-1218","mag":"2799029897"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1218","pdf_url":"https://www.aclweb.org/anthology/P18-1218.pdf","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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-1218.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102395716","display_name":"Hongyu Gong","orcid":"https://orcid.org/0009-0008-3460-241X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hongyu Gong","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061637412","display_name":"Tarek Sakakini","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tarek Sakakini","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083777443","display_name":"Suma Bhat","orcid":"https://orcid.org/0000-0003-0324-5890"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suma Bhat","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030156276","display_name":"Jinjun Xiong","orcid":"https://orcid.org/0000-0002-2620-4859"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"JinJun Xiong","raw_affiliation_strings":["T. J. Watson Research Center, IBM"],"affiliations":[{"raw_affiliation_string":"T. J. Watson Research Center, IBM","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102395716"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":4.7236,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.9585932,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2341","last_page":"2351"},"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":0.9991999864578247,"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":0.7724611163139343},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7156697511672974},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6843591928482056},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.640083909034729},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.639286458492279},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6299108862876892},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5549495816230774},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5226178765296936},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5153328776359558},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.4386487603187561},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4291718900203705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39881840348243713},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3777388334274292},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2731616199016571},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09349840879440308},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.060524165630340576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724611163139343},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7156697511672974},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6843591928482056},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.640083909034729},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.639286458492279},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6299108862876892},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5549495816230774},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5226178765296936},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5153328776359558},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.4386487603187561},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4291718900203705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39881840348243713},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3777388334274292},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2731616199016571},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09349840879440308},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.060524165630340576},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-1218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1218","pdf_url":"https://www.aclweb.org/anthology/P18-1218.pdf","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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1218","pdf_url":"https://www.aclweb.org/anthology/P18-1218.pdf","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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316786","display_name":"Center for Cognitive Computing Systems Research","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2799029897.pdf","grobid_xml":"https://content.openalex.org/works/W2799029897.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W580074167","https://openalex.org/W658020064","https://openalex.org/W1486649854","https://openalex.org/W1523296404","https://openalex.org/W1646006088","https://openalex.org/W1880262756","https://openalex.org/W1978394996","https://openalex.org/W2053186076","https://openalex.org/W2058013187","https://openalex.org/W2075134446","https://openalex.org/W2097120204","https://openalex.org/W2120615054","https://openalex.org/W2125261539","https://openalex.org/W2131744502","https://openalex.org/W2147152072","https://openalex.org/W2147438222","https://openalex.org/W2149557440","https://openalex.org/W2152311353","https://openalex.org/W2153579005","https://openalex.org/W2160471965","https://openalex.org/W2250585720","https://openalex.org/W2250669704","https://openalex.org/W2252022287","https://openalex.org/W2265846598","https://openalex.org/W2571932860","https://openalex.org/W2573127528","https://openalex.org/W2963216505","https://openalex.org/W2963355447","https://openalex.org/W4213009331","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W1501776718","https://openalex.org/W2615136228","https://openalex.org/W2319693127","https://openalex.org/W2072263576","https://openalex.org/W2474567666","https://openalex.org/W2790658443","https://openalex.org/W1940044583","https://openalex.org/W2056226831","https://openalex.org/W2806903871","https://openalex.org/W4320802053"],"abstract_inverted_index":{"Measuring":[0],"similarity":[1,16],"between":[2,45],"texts":[3,75],"is":[4,35],"an":[5],"important":[6],"task":[7],"for":[8,19],"several":[9],"applications.":[10],"Available":[11],"approaches":[12],"to":[13,68,113],"measure":[14],"document":[15,20,30,48,65],"are":[17],"inadequate":[18],"pairs":[21],"that":[22,94],"have":[23],"non-comparable":[24],"lengths,":[25],"such":[26],"as":[27],"a":[28,46,64,77],"long":[29,47],"and":[31,41,52,92,97],"its":[32,53],"summary.":[33],"This":[34],"because":[36],"of":[37,49,56,80,107,110],"the":[38,42,74,85,105,108],"lexical,":[39],"contextual":[40],"abstraction":[43],"gaps":[44],"rich":[50],"details":[51],"concise":[54],"summary":[55],"abstract":[57],"information.":[58],"In":[59],"this":[60,70],"paper,":[61],"we":[62],"present":[63],"matching":[66,86,90],"approach":[67],"bridge":[69],"gap,":[71],"by":[72],"comparing":[73],"in":[76],"common":[78],"space":[79],"hidden":[81],"topics.":[82],"We":[83,102],"evaluate":[84],"algorithm":[87],"on":[88],"two":[89],"tasks":[91],"find":[93],"it":[95],"consistently":[96],"widely":[98],"outperforms":[99],"strong":[100],"baselines.":[101],"also":[103],"highlight":[104],"benefits":[106],"incorporation":[109],"domain":[111],"knowledge":[112],"text":[114],"matching.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}