{"id":"https://openalex.org/W2742155240","doi":"https://doi.org/10.18653/v1/w17-2512","title":"Overview of the Second BUCC Shared Task: Spotting Parallel Sentences in Comparable Corpora","display_name":"Overview of the Second BUCC Shared Task: Spotting Parallel Sentences in Comparable Corpora","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2742155240","doi":"https://doi.org/10.18653/v1/w17-2512","mag":"2742155240"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-2512","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2512","pdf_url":"https://www.aclweb.org/anthology/W17-2512.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 10th Workshop on Building and Using Comparable Corpora","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-2512.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090195478","display_name":"Pierre Zweigenbaum","orcid":"https://orcid.org/0000-0001-8410-4808"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]},{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210151080","display_name":"Hochschule Magdeburg-Stendal","ror":"https://ror.org/04vjfp916","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210151080"]},{"id":"https://openalex.org/I4210155240","display_name":"Canadian Nautical Research Society","ror":"https://ror.org/04zzdbj59","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210155240"]}],"countries":["CA","DE","FR","GB"],"is_corresponding":false,"raw_author_name":"Pierre Zweigenbaum","raw_affiliation_strings":["University of Mainz, Germany","Magdeburg-Stendal University of Applied Sciences and","Universit\u00e9 Paris-Saclay, F-91405 Orsay, France","CNRS,","University of Leeds, Leeds, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Magdeburg-Stendal University of Applied Sciences and","institution_ids":["https://openalex.org/I4210151080"]},{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, F-91405 Orsay, France","institution_ids":["https://openalex.org/I277688954"]},{"raw_affiliation_string":"CNRS,","institution_ids":["https://openalex.org/I4210155240"]},{"raw_affiliation_string":"University of Leeds, Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072701587","display_name":"Serge Sharoff","orcid":"https://orcid.org/0000-0002-4877-0210"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]},{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210151080","display_name":"Hochschule Magdeburg-Stendal","ror":"https://ror.org/04vjfp916","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210151080"]},{"id":"https://openalex.org/I4210155240","display_name":"Canadian Nautical Research Society","ror":"https://ror.org/04zzdbj59","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210155240"]}],"countries":["CA","DE","FR","GB"],"is_corresponding":false,"raw_author_name":"Serge Sharoff","raw_affiliation_strings":["University of Mainz, Germany","University of Leeds, Leeds, United Kingdom","Universit\u00e9 Paris-Saclay, F-91405 Orsay, France","CNRS,","Magdeburg-Stendal University of Applied Sciences and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"University of Leeds, Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]},{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, F-91405 Orsay, France","institution_ids":["https://openalex.org/I277688954"]},{"raw_affiliation_string":"CNRS,","institution_ids":["https://openalex.org/I4210155240"]},{"raw_affiliation_string":"Magdeburg-Stendal University of Applied Sciences and","institution_ids":["https://openalex.org/I4210151080"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049674705","display_name":"Reinhard Rapp","orcid":"https://orcid.org/0000-0002-7245-551X"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]},{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210151080","display_name":"Hochschule Magdeburg-Stendal","ror":"https://ror.org/04vjfp916","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210151080"]},{"id":"https://openalex.org/I4210155240","display_name":"Canadian Nautical Research Society","ror":"https://ror.org/04zzdbj59","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210155240"]}],"countries":["CA","DE","FR","GB"],"is_corresponding":false,"raw_author_name":"Reinhard Rapp","raw_affiliation_strings":["Magdeburg-Stendal University of Applied Sciences and","University of Mainz, Germany","Universit\u00e9 Paris-Saclay, F-91405 Orsay, France","CNRS,","University of Leeds, Leeds, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Magdeburg-Stendal University of Applied Sciences and","institution_ids":["https://openalex.org/I4210151080"]},{"raw_affiliation_string":"University of Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, F-91405 Orsay, France","institution_ids":["https://openalex.org/I277688954"]},{"raw_affiliation_string":"CNRS,","institution_ids":["https://openalex.org/I4210155240"]},{"raw_affiliation_string":"University of Leeds, Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9565,"has_fulltext":true,"cited_by_count":61,"citation_normalized_percentile":{"value":0.96177694,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"60","last_page":"67"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","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/T13629","display_name":"Text Readability and Simplification","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"}}],"keywords":[{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.8436393737792969},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7863914370536804},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.7656527757644653},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7516559958457947},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6865344643592834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6126670837402344},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.5887847542762756},{"id":"https://openalex.org/keywords/gold-standard","display_name":"Gold standard (test)","score":0.5313898324966431},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5149479508399963},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5147114396095276},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3509039282798767},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2627217769622803},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15334653854370117},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1318131685256958},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.09145045280456543}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.8436393737792969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863914370536804},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7656527757644653},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7516559958457947},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6865344643592834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6126670837402344},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.5887847542762756},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.5313898324966431},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5149479508399963},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5147114396095276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3509039282798767},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2627217769622803},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15334653854370117},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1318131685256958},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.09145045280456543},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-2512","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2512","pdf_url":"https://www.aclweb.org/anthology/W17-2512.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 10th Workshop on Building and Using Comparable Corpora","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-2512","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2512","pdf_url":"https://www.aclweb.org/anthology/W17-2512.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 10th Workshop on Building and Using Comparable Corpora","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2742155240.pdf","grobid_xml":"https://content.openalex.org/works/W2742155240.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W8895266","https://openalex.org/W1828724394","https://openalex.org/W2120445606","https://openalex.org/W2166098990","https://openalex.org/W2250288378","https://openalex.org/W2462305634","https://openalex.org/W2508809683","https://openalex.org/W2513660799","https://openalex.org/W2739740656","https://openalex.org/W2740274673","https://openalex.org/W2741268430","https://openalex.org/W2741788241","https://openalex.org/W2791294922","https://openalex.org/W2952037945"],"related_works":["https://openalex.org/W2034439647","https://openalex.org/W3184921334","https://openalex.org/W4249589822","https://openalex.org/W2103063669","https://openalex.org/W4380551034","https://openalex.org/W4386895402","https://openalex.org/W3202382261","https://openalex.org/W4255446307","https://openalex.org/W2315527029","https://openalex.org/W4362466842"],"abstract_inverted_index":{"This":[0,155],"paper":[1],"presents":[2,22],"the":[3,17,20,29,41,50,71,84,87,111,117,124,133,140,148,158,168],"BUCC":[4,159],"2017":[5,160],"shared":[6,42],"task":[7,43],"on":[8],"parallel":[9,94,127,169],"sentence":[10,95,114,128,170],"extraction":[11],"from":[12],"comparable":[13],"corpora.":[14],"It":[15],"recalls":[16],"design":[18,85],"of":[19,49,83,86,110,126,151,167],"datasets,":[21],"their":[23],"final":[24],"construction":[25],"and":[26,28,61,79,122],"statistics":[27],"methods":[30],"used":[31],"to":[32,40,139,144],"evaluate":[33],"system":[34],"results.":[35],"13":[36],"runs":[37,121],"were":[38,74],"submitted":[39],"by":[44],"4":[45],"teams,":[46],"covering":[47],"three":[48],"four":[51],"proposed":[52],"language":[53],"pairs:":[54],"French-English":[55,120,149],"(7":[56],"runs),":[57,60],"German-English":[58],"(3":[59,63],"Chinese-English":[62],"runs).":[64],"The":[65],"best":[66],"F-scores":[67,150],"as":[68],"measured":[69],"against":[70],"gold":[72,93,135,141],"standard":[73,142],"0.84":[75],"(German-English),":[76],"0.80":[77],"(French-English),":[78],"0.43":[80],"(Chinese-English).":[81],"Because":[82],"dataset,":[88],"in":[89,132],"which":[90],"not":[91,130],"all":[92],"pairs":[96,115,129],"are":[97,100],"known,":[98],"these":[99],"only":[101],"minimum":[102],"values.":[103],"We":[104],"examined":[105],"manually":[106],"a":[107,163],"small":[108],"sample":[109],"false":[112],"negative":[113],"for":[116,147],"most":[118,153],"precise":[119],"estimated":[123],"number":[125],"yet":[131],"provided":[134],"standard.":[136],"Adding":[137],"them":[138],"leads":[143],"revised":[145],"estimates":[146],"at":[152],"+1.5pt.":[154],"suggests":[156],"that":[157],"datasets":[161],"provide":[162],"reasonable":[164],"approximate":[165],"evaluation":[166],"spotting":[171],"task.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}
