{"id":"https://openalex.org/W2740274673","doi":"https://doi.org/10.18653/v1/w17-2511","title":"BUCC2017: A Hybrid Approach for Identifying Parallel Sentences in Comparable Corpora","display_name":"BUCC2017: A Hybrid Approach for Identifying Parallel Sentences in Comparable Corpora","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2740274673","doi":"https://doi.org/10.18653/v1/w17-2511","mag":"2740274673"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-2511","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2511","pdf_url":"https://www.aclweb.org/anthology/W17-2511.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/W17-2511.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005052090","display_name":"Sainik Kumar Mahata","orcid":"https://orcid.org/0000-0003-1041-0129"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sainik Mahata","raw_affiliation_strings":["Department of Computer Science and Engineering, Jadavpur University, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Jadavpur University, India","institution_ids":["https://openalex.org/I170979836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052810907","display_name":"Dipankar Das","orcid":"https://orcid.org/0000-0002-8110-9344"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Dipankar Das","raw_affiliation_strings":["Department of Computer Science and Engineering, Jadavpur University, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Jadavpur University, India","institution_ids":["https://openalex.org/I170979836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006218020","display_name":"Sivaji Bandyopadhyay","orcid":"https://orcid.org/0000-0003-2607-1774"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sivaji Bandyopadhyay","raw_affiliation_strings":["Department of Computer Science and Engineering, Jadavpur University, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Jadavpur University, India","institution_ids":["https://openalex.org/I170979836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052810907"],"corresponding_institution_ids":["https://openalex.org/I170979836"],"apc_list":null,"apc_paid":null,"fwci":1.5602,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87279541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"59"},"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":0.9987999796867371,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8753465414047241},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.7737005949020386},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7629390954971313},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.736459493637085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6974928379058838},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6451598405838013},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6451443433761597},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6206705570220947},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6197704076766968},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5608594417572021},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5466974973678589},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4843407869338989},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.442732036113739},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.43077489733695984},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3571658730506897},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.12641692161560059},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08890113234519958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8753465414047241},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.7737005949020386},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7629390954971313},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.736459493637085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6974928379058838},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6451598405838013},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6451443433761597},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6206705570220947},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6197704076766968},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5608594417572021},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5466974973678589},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4843407869338989},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.442732036113739},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.43077489733695984},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3571658730506897},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.12641692161560059},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08890113234519958},{"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-2511","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2511","pdf_url":"https://www.aclweb.org/anthology/W17-2511.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/w17-2511","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2511","pdf_url":"https://www.aclweb.org/anthology/W17-2511.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":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740274673.pdf","grobid_xml":"https://content.openalex.org/works/W2740274673.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1543107604","https://openalex.org/W2000748429","https://openalex.org/W2115755647","https://openalex.org/W2117652747","https://openalex.org/W2123282296","https://openalex.org/W2125197186","https://openalex.org/W2136439896","https://openalex.org/W2138553032","https://openalex.org/W2138584836","https://openalex.org/W2161895154","https://openalex.org/W2166606631","https://openalex.org/W2251569308","https://openalex.org/W2507478797","https://openalex.org/W2610740672"],"related_works":["https://openalex.org/W2786253471","https://openalex.org/W4293584592","https://openalex.org/W2986030184","https://openalex.org/W2104907655","https://openalex.org/W4287212313","https://openalex.org/W2985215540","https://openalex.org/W3155572818","https://openalex.org/W2913434276","https://openalex.org/W3175595715","https://openalex.org/W3152052241"],"abstract_inverted_index":{"A":[0],"Statistical":[1],"Machine":[2],"Translation":[3],"(SMT)":[4],"system":[5,99],"is":[6,19,47],"always":[7],"trained":[8],"using":[9],"large":[10],"parallel":[11,66],"corpus":[12,21,34,67],"to":[13,53,63,123],"produce":[14],"effective":[15],"translation.":[16],"Not":[17],"only":[18],"the":[20,54,58,80,88,103,113,121],"scarce,":[22],"it":[23],"also":[24],"involves":[25],"a":[26,43,65,73,98],"lot":[27],"of":[28,45,87],"manual":[29],"labor":[30],"and":[31,79,110],"cost.":[32],"Parallel":[33],"can":[35],"be":[36],"prepared":[37],"by":[38,92,105],"employing":[39],"comparable":[40,75],"corpora":[41,46],"where":[42],"pair":[44,71],"in":[48],"two":[49],"different":[50],"languages":[51],"pointing":[52],"same":[55],"domain.":[56],"In":[57],"present":[59],"work,":[60],"we":[61],"try":[62],"build":[64],"for":[68],"French-English":[69],"language":[70],"from":[72],"given":[74],"corpus.":[76],"The":[77],"data":[78],"problem":[81],"set":[82],"are":[83],"provided":[84],"as":[85],"part":[86],"shared":[89],"task":[90],"organized":[91],"BUCC":[93],"2017.":[94],"We":[95],"have":[96],"proposed":[97],"that":[100],"first":[101],"translates":[102],"sentences":[104,114],"heavily":[106],"relying":[107],"on":[108,116,130],"Moses":[109],"then":[111],"group":[112],"based":[115,129],"sentence":[117,125],"length":[118],"similarity.":[119],"Finally,":[120],"one":[122,124],"selection":[126],"was":[127],"done":[128],"Cosine":[131],"Similarity":[132],"algorithm.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}