{"id":"https://openalex.org/W2990238801","doi":"https://doi.org/10.26615/978-954-452-056-4_070","title":"Question Similarity in Community Question Answering: A Systematic Exploration of Preprocessing Methods and Models","display_name":"Question Similarity in Community Question Answering: A Systematic Exploration of Preprocessing Methods and Models","publication_year":2019,"publication_date":"2019-10-22","ids":{"openalex":"https://openalex.org/W2990238801","doi":"https://doi.org/10.26615/978-954-452-056-4_070","mag":"2990238801"},"language":"en","primary_location":{"id":"doi:10.26615/978-954-452-056-4_070","is_oa":true,"landing_page_url":"https://doi.org/10.26615/978-954-452-056-4_070","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_070","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.26615/978-954-452-056-4_070","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063456893","display_name":"Florian Kunneman","orcid":"https://orcid.org/0000-0002-1932-3200"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Florian Kunneman","raw_affiliation_strings":["Centre for Language Studies, Radboud University, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Language Studies, Radboud University, The Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101930005","display_name":"Thiago Castro Ferreira","orcid":"https://orcid.org/0000-0003-0200-3646"},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]},{"id":"https://openalex.org/I4210158762","display_name":"Meertens Institute","ror":"https://ror.org/05kaxyq51","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1322597698","https://openalex.org/I4210158762"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Thiago Castro Ferreira","raw_affiliation_strings":["C KNAW Meertens Institute, Amsterdam, The Netherlands","Tilburg center for Cognition and Communication, Tilburg University, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"C KNAW Meertens Institute, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I4210158762"]},{"raw_affiliation_string":"Tilburg center for Cognition and Communication, Tilburg University, The Netherlands","institution_ids":["https://openalex.org/I193700539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069734813","display_name":"Emiel Krahmer","orcid":"https://orcid.org/0000-0002-6304-7549"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emiel Krahmer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031562992","display_name":"Antal van den Bosch","orcid":"https://orcid.org/0000-0003-2493-656X"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]},{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]},{"id":"https://openalex.org/I4210158762","display_name":"Meertens Institute","ror":"https://ror.org/05kaxyq51","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1322597698","https://openalex.org/I4210158762"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Antal van den Bosch","raw_affiliation_strings":["Centre for Language Studies, Radboud University, The Netherlands","Tilburg center for Cognition and Communication, Tilburg University, The Netherlands","C KNAW Meertens Institute, Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Language Studies, Radboud University, The Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Tilburg center for Cognition and Communication, Tilburg University, The Netherlands","institution_ids":["https://openalex.org/I193700539"]},{"raw_affiliation_string":"C KNAW Meertens Institute, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I4210158762"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"593","last_page":"601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9979000091552734,"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":0.9970999956130981,"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":0.8426298499107361},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6822367906570435},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.671241819858551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6426100730895996},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.6402814388275146},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6154077649116516},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5919206738471985},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5907794237136841},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5470623970031738},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5450241565704346},{"id":"https://openalex.org/keywords/stop-words","display_name":"Stop words","score":0.5402384400367737},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5085269212722778},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4675782024860382},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46042490005493164},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.45562270283699036},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4141084551811218},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15771368145942688},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12075638771057129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8426298499107361},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6822367906570435},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.671241819858551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6426100730895996},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.6402814388275146},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6154077649116516},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5919206738471985},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5907794237136841},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5470623970031738},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5450241565704346},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.5402384400367737},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5085269212722778},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4675782024860382},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46042490005493164},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.45562270283699036},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4141084551811218},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15771368145942688},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12075638771057129},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"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/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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":4,"locations":[{"id":"doi:10.26615/978-954-452-056-4_070","is_oa":true,"landing_page_url":"https://doi.org/10.26615/978-954-452-056-4_070","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_070","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.knaw.nl:publications/943d268c-8e00-4433-9882-c159c0f64a63","is_oa":true,"landing_page_url":"https://pure.knaw.nl/portal/en/publications/943d268c-8e00-4433-9882-c159c0f64a63","pdf_url":null,"source":{"id":"https://openalex.org/S4306400439","display_name":"KNAW Research Portal (The Royal Netherlands Academy of Arts and Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.knaw.nl:openaire/943d268c-8e00-4433-9882-c159c0f64a63","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11755/943d268c-8e00-4433-9882-c159c0f64a63","pdf_url":null,"source":{"id":"https://openalex.org/S4306400439","display_name":"KNAW Research Portal (The Royal Netherlands Academy of Arts and Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:uvt:oai:tilburguniversity.edu:publications/a902f25b-c58e-4e64-a20a-201b58eb5fb2","is_oa":true,"landing_page_url":"https://research.tilburguniversity.edu/en/publications/a902f25b-c58e-4e64-a20a-201b58eb5fb2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of Recent Advances in Natural Language Processing (RANLP 2019), 593 - 601","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"doi:10.26615/978-954-452-056-4_070","is_oa":true,"landing_page_url":"https://doi.org/10.26615/978-954-452-056-4_070","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_070","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2990238801.pdf","grobid_xml":"https://content.openalex.org/works/W2990238801.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W151785663","https://openalex.org/W1587871245","https://openalex.org/W1854214752","https://openalex.org/W2030750105","https://openalex.org/W2101234009","https://openalex.org/W2141599568","https://openalex.org/W2143017621","https://openalex.org/W2147308966","https://openalex.org/W2155482025","https://openalex.org/W2162355876","https://openalex.org/W2466490286","https://openalex.org/W2468484304","https://openalex.org/W2468672598","https://openalex.org/W2493916176","https://openalex.org/W2751698296","https://openalex.org/W2915240437","https://openalex.org/W2962739339","https://openalex.org/W4245267204","https://openalex.org/W4252076394"],"related_works":["https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W3107848922","https://openalex.org/W4236441695","https://openalex.org/W3194154551","https://openalex.org/W3194543085","https://openalex.org/W3101676040"],"abstract_inverted_index":{"Community":[0],"Question":[1],"Answering":[2],"forums":[3],"are":[4],"popular":[5],"among":[6],"Internet":[7],"users,":[8],"and":[9,87,104,114,129,133,146],"a":[10],"basic":[11],"problem":[12],"they":[13,92],"encounter":[14],"is":[15,173],"trying":[16],"to":[17,37,75,159],"find":[18],"out":[19],"if":[20],"their":[21,78],"question":[22],"has":[23],"already":[24],"been":[25],"posed":[26],"before.":[27],"To":[28],"address":[29],"this":[30,55,98],"issue,":[31],"NLP":[32],"researchers":[33],"have":[34],"developed":[35],"methods":[36,73,86],"automatically":[38],"detect":[39],"question-similarity,":[40],"which":[41],"was":[42],"one":[43],"of":[44,59,90,122,127,151],"the":[45,64,110,120,149,152,163,168],"shared":[46],"tasks":[47],"in":[48,165],"Se-mEval.":[49],"The":[50,171],"best":[51],"performing":[52],"systems":[53],"for":[54],"task":[56],"made":[57,174],"use":[58],"Syntactic":[60],"Tree":[61],"Kernels":[62],"or":[63],"SoftCosine":[65],"metric.":[66],"However,":[67],"it":[68],"remains":[69],"unclear":[70],"why":[71],"these":[72,106],"seem":[74],"work,":[76],"whether":[77],"performance":[79,150,166],"can":[80],"be":[81],"improved":[82],"by":[83],"better":[84],"preprocessing":[85,123],"what":[88],"kinds":[89],"errors":[91],"(and":[93],"other":[94],"methods)":[95],"make.":[96],"In":[97],"paper,":[99],"we":[100,118],"therefore":[101],"systematically":[102],"combine":[103],"compare":[105],"two":[107],"approaches":[108],"with":[109],"more":[111],"traditional":[112],"BM25":[113],"translation-based":[115],"models.":[116],"Moreover,":[117],"analyze":[119],"impact":[121],"steps":[124],"(lowercasing,":[125],"suppression":[126],"punctuation":[128],"stop":[130],"words":[131],"removal)":[132],"word":[134],"meaning":[135],"similarity":[136],"based":[137],"on":[138,148],"different":[139],"distributions":[140],"(word":[141],"translation":[142],"probability,":[143],"Word2Vec,":[144],"fastText":[145],"ELMo)":[147],"task.":[153],"We":[154],"conduct":[155],"an":[156],"error":[157],"analysis":[158],"gain":[160],"insight":[161],"into":[162],"differences":[164],"between":[167],"system":[169],"set-ups.":[170],"implementation":[172],"publicly":[175],"available.":[176],"1":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}