{"id":"https://openalex.org/W2988853560","doi":"https://doi.org/10.18653/v1/k19-1005","title":"Large-Scale, Diverse, Paraphrastic Bitexts via Sampling and Clustering","display_name":"Large-Scale, Diverse, Paraphrastic Bitexts via Sampling and Clustering","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2988853560","doi":"https://doi.org/10.18653/v1/k19-1005","mag":"2988853560"},"language":"en","primary_location":{"id":"doi:10.18653/v1/k19-1005","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1005","pdf_url":"https://www.aclweb.org/anthology/K19-1005.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 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/K19-1005.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103230101","display_name":"J. Edward Hu","orcid":"https://orcid.org/0000-0002-5557-6790"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"J. Edward Hu","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103579400","display_name":"Abhinav Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Singh","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017498603","display_name":"Nils Holzenberger","orcid":"https://orcid.org/0000-0002-0844-1391"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nils Holzenberger","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108266978","display_name":"Matt Post","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matt Post","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075825791","display_name":"Benjamin Van Durme","orcid":"https://orcid.org/0000-0003-4328-4288"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Van Durme","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103230101"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":2.7456,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.92700103,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8928171396255493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8112519979476929},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7179980874061584},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7105798721313477},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6918022632598877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6693717837333679},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6304370164871216},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5447805523872375},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5353116989135742},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5229561924934387},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.5014393329620361},{"id":"https://openalex.org/keywords/lexical-diversity","display_name":"Lexical diversity","score":0.47227582335472107},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4717719554901123},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4478147029876709},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.44248145818710327},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20726701617240906},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.105826735496521}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.8928171396255493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8112519979476929},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7179980874061584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7105798721313477},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6918022632598877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6693717837333679},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6304370164871216},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5447805523872375},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5353116989135742},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5229561924934387},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.5014393329620361},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.47227582335472107},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4717719554901123},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4478147029876709},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.44248145818710327},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20726701617240906},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.105826735496521},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/k19-1005","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1005","pdf_url":"https://www.aclweb.org/anthology/K19-1005.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 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/k19-1005","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1005","pdf_url":"https://www.aclweb.org/anthology/K19-1005.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 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G531346954","display_name":"Collaborative Research:  The MegaAttitude Project: Investigating selection and polysemy at the scale of the lexicon","funder_award_id":"1749025","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G784659618","display_name":null,"funder_award_id":"1748969","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2988853560.pdf","grobid_xml":"https://content.openalex.org/works/W2988853560.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1493309689","https://openalex.org/W1579035156","https://openalex.org/W1583990341","https://openalex.org/W1980776243","https://openalex.org/W2028509346","https://openalex.org/W2051593977","https://openalex.org/W2061433145","https://openalex.org/W2064675550","https://openalex.org/W2081580037","https://openalex.org/W2099884836","https://openalex.org/W2107130271","https://openalex.org/W2115259925","https://openalex.org/W2115792525","https://openalex.org/W2118021410","https://openalex.org/W2123442489","https://openalex.org/W2125313055","https://openalex.org/W2131726681","https://openalex.org/W2136189984","https://openalex.org/W2144108169","https://openalex.org/W2250225488","https://openalex.org/W2251044566","https://openalex.org/W2251386628","https://openalex.org/W2251882135","https://openalex.org/W2294860948","https://openalex.org/W2461708070","https://openalex.org/W2462305634","https://openalex.org/W2472403012","https://openalex.org/W2493109812","https://openalex.org/W2512924740","https://openalex.org/W2515295520","https://openalex.org/W2736149021","https://openalex.org/W2742148828","https://openalex.org/W2778814079","https://openalex.org/W2888868988","https://openalex.org/W2889326796","https://openalex.org/W2895988667","https://openalex.org/W2896457183","https://openalex.org/W2897820187","https://openalex.org/W2898837495","https://openalex.org/W2921806258","https://openalex.org/W2923014074","https://openalex.org/W2963126845","https://openalex.org/W2963281280","https://openalex.org/W2963310665","https://openalex.org/W2963323070","https://openalex.org/W2963341956","https://openalex.org/W2963352809","https://openalex.org/W2963403868","https://openalex.org/W2963499246","https://openalex.org/W2963846996","https://openalex.org/W2963979492","https://openalex.org/W2964053384","https://openalex.org/W2964212550","https://openalex.org/W2964213257","https://openalex.org/W3082674894","https://openalex.org/W4295803813","https://openalex.org/W4297801368","https://openalex.org/W4385245566","https://openalex.org/W4386506836"],"related_works":["https://openalex.org/W4321512656","https://openalex.org/W4212936623","https://openalex.org/W2216851945","https://openalex.org/W3118824058","https://openalex.org/W3048733152","https://openalex.org/W4287690375","https://openalex.org/W3197133407","https://openalex.org/W4378713476","https://openalex.org/W1518159552","https://openalex.org/W2885514718"],"abstract_inverted_index":{"Producing":[0],"diverse":[1,46],"paraphrases":[2],"of":[3],"a":[4,7,40,51],"sentence":[5],"is":[6],"challenging":[8],"task.":[9],"Natural":[10],"paraphrase":[11],"corpora":[12],"are":[13,21],"scarce":[14],"and":[15,26,59,73,84],"limited,":[16],"while":[17,76],"existing":[18],"large-scale":[19],"resources":[20,93],"automatically":[22],"generated":[23],"via":[24],"back-translation":[25],"rely":[27],"on":[28],"beam":[29],"search,":[30],"which":[31],"tends":[32],"to":[33,97,102],"lack":[34],"diversity.":[35],"We":[36,61],"describe":[37],"PARABANK":[38,64],"2,":[39],"new":[41],"resource":[42],"that":[43,63],"contains":[44],"multiple":[45],"sentential":[47],"paraphrases,":[48],"produced":[49],"from":[50],"bilingual":[52],"corpus":[53],"using":[54],"negative":[55],"constraints,":[56],"inference":[57],"sampling,":[58],"clustering.":[60],"show":[62],"2":[65],"significantly":[66],"surpasses":[67],"prior":[68],"work":[69],"in":[70,104],"both":[71],"lexical":[72],"syntactic":[74],"diversity":[75],"being":[77],"meaningpreserving,":[78],"as":[79],"measured":[80],"by":[81],"human":[82],"judgments":[83],"standardized":[85],"metrics.":[86],"Further,":[87],"we":[88],"illustrate":[89],"how":[90],"such":[91],"paraphrastic":[92],"may":[94],"be":[95],"used":[96],"refine":[98],"contextualized":[99],"encoders,":[100],"leading":[101],"improvements":[103],"downstream":[105],"tasks.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}