{"id":"https://openalex.org/W2513768144","doi":"https://doi.org/10.18653/v1/w16-2369","title":"First Steps Towards Coverage-Based Document Alignment","display_name":"First Steps Towards Coverage-Based Document Alignment","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2513768144","doi":"https://doi.org/10.18653/v1/w16-2369","mag":"2513768144"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2369","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2369","pdf_url":"https://www.aclweb.org/anthology/W16-2369.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 First Conference on Machine Translation: Volume 2,\n          Shared Task Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-2369.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016860678","display_name":"Lu\u00eds Gomes","orcid":"https://orcid.org/0000-0003-3119-4189"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]},{"id":"https://openalex.org/I2800474387","display_name":"Vodafone (Portugal)","ror":"https://ror.org/00y7x8f51","country_code":"PT","type":"company","lineage":["https://openalex.org/I2800474387","https://openalex.org/I74316835"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Lu\u00eds Gomes","raw_affiliation_strings":["ISTRION BOX, Translation and Revision, Lda, Portugal","NOVA LINCS, Faculdade de Cincias e Tecnologia, Universidade Nova de Lisboa, Portugal","NOVA LINCS, Faculdade de Ci\u00eancias e Tecnologia, Universidade Nova de Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"ISTRION BOX, Translation and Revision, Lda, Portugal","institution_ids":["https://openalex.org/I2800474387"]},{"raw_affiliation_string":"NOVA LINCS, Faculdade de Cincias e Tecnologia, Universidade Nova de Lisboa, Portugal","institution_ids":["https://openalex.org/I83558840"]},{"raw_affiliation_string":"NOVA LINCS, Faculdade de Ci\u00eancias e Tecnologia, Universidade Nova de Lisboa, Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019773155","display_name":"Gabriel Pereira Lopes","orcid":"https://orcid.org/0000-0003-1669-0336"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]},{"id":"https://openalex.org/I2800474387","display_name":"Vodafone (Portugal)","ror":"https://ror.org/00y7x8f51","country_code":"PT","type":"company","lineage":["https://openalex.org/I2800474387","https://openalex.org/I74316835"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Gabriel Pereira Lopes","raw_affiliation_strings":["ISTRION BOX, Translation and Revision, Lda, Portugal","NOVA LINCS, Faculdade de Cincias e Tecnologia, Universidade Nova de Lisboa, Portugal","NOVA LINCS, Faculdade de Ci\u00eancias e Tecnologia, Universidade Nova de Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"ISTRION BOX, Translation and Revision, Lda, Portugal","institution_ids":["https://openalex.org/I2800474387"]},{"raw_affiliation_string":"NOVA LINCS, Faculdade de Cincias e Tecnologia, Universidade Nova de Lisboa, Portugal","institution_ids":["https://openalex.org/I83558840"]},{"raw_affiliation_string":"NOVA LINCS, Faculdade de Ci\u00eancias e Tecnologia, Universidade Nova de Lisboa, Portugal","institution_ids":["https://openalex.org/I83558840"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016860678"],"corresponding_institution_ids":["https://openalex.org/I2800474387","https://openalex.org/I83558840"],"apc_list":null,"apc_paid":null,"fwci":2.2086,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.90916228,"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":"697","last_page":"702"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T11269","display_name":"Algorithms and Data Compression","score":0.9983999729156494,"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":0.996999979019165,"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/phrase","display_name":"Phrase","score":0.8479146957397461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8132976293563843},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5848244428634644},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4713306427001953},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4678497910499573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35566672682762146}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8479146957397461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132976293563843},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5848244428634644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4713306427001953},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4678497910499573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35566672682762146},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/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/w16-2369","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2369","pdf_url":"https://www.aclweb.org/anthology/W16-2369.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 First Conference on Machine Translation: Volume 2,\n          Shared Task Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2369","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2369","pdf_url":"https://www.aclweb.org/anthology/W16-2369.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 First Conference on Machine Translation: Volume 2,\n          Shared Task Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1113003032","display_name":null,"funder_award_id":"UID/CEC/04516/2013","funder_id":"https://openalex.org/F4320331406","funder_display_name":"NOVA Laboratory for Computer Science and Informatics"},{"id":"https://openalex.org/G3284537356","display_name":null,"funder_award_id":"SFRH/B","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G5818630289","display_name":null,"funder_award_id":"SFRH/BD/","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G6178031923","display_name":null,"funder_award_id":"UID/CEC/04516/2013","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G6299983296","display_name":null,"funder_award_id":"PTDC/","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G7049410507","display_name":null,"funder_award_id":"Portuguese Foundation for Science","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G724804869","display_name":null,"funder_award_id":"SFRH/","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320331406","display_name":"NOVA Laboratory for Computer Science and Informatics","ror":null},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2513768144.pdf","grobid_xml":"https://content.openalex.org/works/W2513768144.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W2124807415","https://openalex.org/W2153488166","https://openalex.org/W2574732135","https://openalex.org/W2595715041","https://openalex.org/W2787646045"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W2060629350","https://openalex.org/W2357294589","https://openalex.org/W2386861027","https://openalex.org/W2349302580","https://openalex.org/W2390154576","https://openalex.org/W2916983164","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"describe":[4],"a":[5,16,22,36],"method":[6],"for":[7],"selecting":[8],"pairs":[9,47,74,82],"of":[10,18,25,43,52,59,83,97],"parallel":[11,66],"documents":[12,26,67,84],"(documents":[13],"that":[14,39],"are":[15],"translation":[17],"each":[19,50],"other)":[20],"from":[21,28,90],"large":[23],"collection":[24],"obtained":[27],"the":[29,41,56,86,98],"web.":[30],"Our":[31],"approach":[32],"is":[33],"based":[34],"on":[35],"coverage":[37,88],"score":[38,89],"reflects":[40],"number":[42,58],"distinct":[44],"bilingual":[45,72],"phrase":[46,73],"found":[48,62],"in":[49,63],"pair":[51],"documents,":[53,77],"normalized":[54],"by":[55],"total":[57],"unique":[60],"phrases":[61],"them.":[64],"Since":[65],"tend":[68],"to":[69],"share":[70],"more":[71],"than":[75],"non-parallel":[76],"our":[78],"alignment":[79],"algorithm":[80],"selects":[81],"with":[85],"maximum":[87],"all":[91],"possible":[92],"pairings":[93],"involving":[94],"either":[95],"one":[96],"two":[99],"documents.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
