{"id":"https://openalex.org/W2153702313","doi":"https://doi.org/10.1162/tacl_a_00194","title":"Extracting Lexically Divergent Paraphrases from Twitter","display_name":"Extracting Lexically Divergent Paraphrases from Twitter","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2153702313","doi":"https://doi.org/10.1162/tacl_a_00194","mag":"2153702313"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00194","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00194","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00194","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00194","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070905937","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-7044-3232"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Xu","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA,","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039096905","display_name":"Alan Ritter","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alan Ritter","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA,","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068508539","display_name":"Chris Callison-Burch","orcid":"https://orcid.org/0000-0001-8196-1943"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chris Callison-Burch","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA,","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043163116","display_name":"William B. Dolan","orcid":null},"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":true,"raw_author_name":"William B. Dolan","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA,","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085302513","display_name":"Yangfeng Ji","orcid":"https://orcid.org/0000-0002-7793-486X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yangfeng Ji","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA,","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039096905","https://openalex.org/A5043163116","https://openalex.org/A5068508539","https://openalex.org/A5070905937","https://openalex.org/A5085302513"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I130701444","https://openalex.org/I52357470","https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":21.1232,"has_fulltext":true,"cited_by_count":117,"citation_normalized_percentile":{"value":0.99463964,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"2","issue":null,"first_page":"435","last_page":"448"},"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":0.9995999932289124,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"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/paraphrase","display_name":"Paraphrase","score":0.9765787720680237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8562003374099731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.72059565782547},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6940200328826904},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6659169793128967},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6047716736793518},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5871332883834839},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.5135958194732666},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5065115690231323},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.28746771812438965}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.9765787720680237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8562003374099731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.72059565782547},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6940200328826904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6659169793128967},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6047716736793518},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5871332883834839},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.5135958194732666},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5065115690231323},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28746771812438965},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1162/tacl_a_00194","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00194","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00194","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.671.2489","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.671.2489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.upenn.edu/%7Exwe/publications/tacl2014-extracting-paraphrases-from-twitter.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.723.3844","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.723.3844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cis.upenn.edu/%7Eccb/publications/extracting-paraphrases-from-twitter.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:6c6f35c7dad342d7803a213b37673631","is_oa":false,"landing_page_url":"https://doaj.org/article/6c6f35c7dad342d7803a213b37673631","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 2 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00194","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00194","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00194","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G4233727642","display_name":"EAGER: Simplification as Machine Translation","funder_award_id":"1430651","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2153702313.pdf","grobid_xml":"https://content.openalex.org/works/W2153702313.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W19551284","https://openalex.org/W46452414","https://openalex.org/W100656083","https://openalex.org/W131533222","https://openalex.org/W138005451","https://openalex.org/W157541337","https://openalex.org/W174427690","https://openalex.org/W191409295","https://openalex.org/W1493309689","https://openalex.org/W1498924130","https://openalex.org/W1520917717","https://openalex.org/W1604644367","https://openalex.org/W1901600440","https://openalex.org/W1947252915","https://openalex.org/W1980776243","https://openalex.org/W1988012253","https://openalex.org/W1989420837","https://openalex.org/W1998498767","https://openalex.org/W2008127487","https://openalex.org/W2008652694","https://openalex.org/W2016172157","https://openalex.org/W2051593977","https://openalex.org/W2051840895","https://openalex.org/W2088911157","https://openalex.org/W2099884836","https://openalex.org/W2104411075","https://openalex.org/W2105846817","https://openalex.org/W2110119381","https://openalex.org/W2111742432","https://openalex.org/W2116064496","https://openalex.org/W2116780029","https://openalex.org/W2116900724","https://openalex.org/W2121495183","https://openalex.org/W2123661878","https://openalex.org/W2132679783","https://openalex.org/W2135875128","https://openalex.org/W2137553870","https://openalex.org/W2138738738","https://openalex.org/W2141766660","https://openalex.org/W2143564602","https://openalex.org/W2146007434","https://openalex.org/W2161925960","https://openalex.org/W2164290393","https://openalex.org/W2164479068","https://openalex.org/W2166245164","https://openalex.org/W2168579166","https://openalex.org/W2250265269","https://openalex.org/W2250293945","https://openalex.org/W2250305120","https://openalex.org/W2250565861","https://openalex.org/W2251149243","https://openalex.org/W2251199281","https://openalex.org/W2251861449","https://openalex.org/W2251898928","https://openalex.org/W2588710172","https://openalex.org/W3105439152"],"related_works":["https://openalex.org/W2376415519","https://openalex.org/W4294769427","https://openalex.org/W1601381279","https://openalex.org/W1895908943","https://openalex.org/W4225667838","https://openalex.org/W3195775898","https://openalex.org/W4287024084","https://openalex.org/W4321512656","https://openalex.org/W2354515814","https://openalex.org/W2349392800"],"abstract_inverted_index":{"We":[0,20,107],"present":[1,91],"MultiP":[2],"(Multi-instance":[3],"Learning":[4],"Paraphrase":[5],"Model),":[6],"a":[7,50,55,60,92,102],"new":[8,110],"model":[9,22,42,58,65,80],"suited":[10],"to":[11,100,113],"identify":[12],"paraphrases":[13,70],"within":[14],"the":[15,46,86,114],"short":[16],"messages":[17],"on":[18],"Twitter.":[19,106],"jointly":[21],"paraphrase":[23,103],"relations":[24],"between":[25],"word":[26],"and":[27,30],"sentence":[28],"pairs":[29],"assume":[31],"only":[32],"sentence-level":[33],"annotations":[34],"during":[35],"learning.":[36],"Using":[37],"this":[38,109],"principled":[39],"latent":[40,56],"variable":[41],"alone,":[43],"we":[44,90],"achieve":[45],"performance":[47],"competitive":[48],"with":[49,59,81],"state-of-the-art":[51],"method":[52],"which":[53],"combines":[54],"space":[57],"feature-based":[61],"supervised":[62],"classifier.":[63],"Our":[64],"also":[66],"captures":[67],"lexically":[68],"divergent":[69],"that":[71,96],"differ":[72],"from":[73,105],"yet":[74],"complement":[75],"previous":[76,82],"methods;":[77],"combining":[78],"our":[79],"work":[83],"significantly":[84],"outperforms":[85],"state-of-the-art.":[87],"In":[88],"addition,":[89],"novel":[93],"annotation":[94],"methodology":[95],"has":[97],"allowed":[98],"us":[99],"crowdsource":[101],"corpus":[104],"make":[108],"dataset":[111],"available":[112],"research":[115],"community.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}