{"id":"https://openalex.org/W2741788241","doi":"https://doi.org/10.18653/v1/w17-2508","title":"Weighted Set-Theoretic Alignment of Comparable Sentences","display_name":"Weighted Set-Theoretic Alignment of Comparable Sentences","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2741788241","doi":"https://doi.org/10.18653/v1/w17-2508","mag":"2741788241"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-2508","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2508","pdf_url":"https://www.aclweb.org/anthology/W17-2508.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-2508.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085424842","display_name":"Andoni Azpeitia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Andoni Azpeitia","raw_affiliation_strings":["Vicomtech-IK4 Mikeletegi Pasalekua, 57 Donostia / San Sebastian, Gipuzkoa, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vicomtech-IK4 Mikeletegi Pasalekua, 57 Donostia / San Sebastian, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087412588","display_name":"Thierry Etchegoyhen","orcid":"https://orcid.org/0000-0001-7253-1693"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Thierry Etchegoyhen","raw_affiliation_strings":["Vicomtech-IK4 Mikeletegi Pasalekua, 57 Donostia / San Sebastian, Gipuzkoa, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vicomtech-IK4 Mikeletegi Pasalekua, 57 Donostia / San Sebastian, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055241434","display_name":"Eva Mart\u00ednez Garc\u00eda","orcid":"https://orcid.org/0000-0002-1071-8230"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eva Mart\u00ednez Garcia","raw_affiliation_strings":["Vicomtech-IK4 Mikeletegi Pasalekua, 57 Donostia / San Sebastian, Gipuzkoa, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vicomtech-IK4 Mikeletegi Pasalekua, 57 Donostia / San Sebastian, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210092551"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210092551"],"apc_list":null,"apc_paid":null,"fwci":1.938,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.90364177,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"45"},"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":0.9998000264167786,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9961000084877014,"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/weighting","display_name":"Weighting","score":0.8125829696655273},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8061859607696533},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.7104180455207825},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7044596076011658},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6442427635192871},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.642986536026001},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5679375529289246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5502628087997437},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5459607243537903},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35088783502578735},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3204197883605957},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1231575608253479},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11913260817527771},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05419960618019104}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8125829696655273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061859607696533},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.7104180455207825},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7044596076011658},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6442427635192871},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.642986536026001},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5679375529289246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5502628087997437},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5459607243537903},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35088783502578735},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3204197883605957},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1231575608253479},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11913260817527771},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05419960618019104},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-2508","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2508","pdf_url":"https://www.aclweb.org/anthology/W17-2508.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/w17-2508","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2508","pdf_url":"https://www.aclweb.org/anthology/W17-2508.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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321705","display_name":"Eusko Jaurlaritza","ror":"https://ror.org/00pz2fp31"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2741788241.pdf","grobid_xml":"https://content.openalex.org/works/W2741788241.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W614252839","https://openalex.org/W630532510","https://openalex.org/W1511653464","https://openalex.org/W1973152633","https://openalex.org/W2061118075","https://openalex.org/W2097333193","https://openalex.org/W2104103102","https://openalex.org/W2105673178","https://openalex.org/W2107695330","https://openalex.org/W2133564696","https://openalex.org/W2141068210","https://openalex.org/W2153579005","https://openalex.org/W2156985047","https://openalex.org/W2159872955","https://openalex.org/W2513660799","https://openalex.org/W2579327808","https://openalex.org/W2588710172","https://openalex.org/W2964308564","https://openalex.org/W4285719527","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W4206560911","https://openalex.org/W2043505748"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"the":[3,8,66,70],"STACC":[4,22],"w":[5],"system":[6],"for":[7,69],"BUCC":[9],"2017":[10],"shared":[11,71],"task":[12],"on":[13,25,65],"parallel":[14],"sentence":[15],"extraction":[16],"from":[17],"comparable":[18],"corpora.":[19],"The":[20],"original":[21],"approach,":[23],"based":[24],"set-theoretic":[26],"operations":[27],"over":[28],"bags":[29],"of":[30,50],"words,":[31],"had":[32],"been":[33],"previously":[34],"shown":[35],"to":[36],"be":[37],"efficient":[38],"and":[39,43,58],"portable":[40],"across":[41],"domains":[42],"alignment":[44],"scenarios.":[45],"We":[46],"describe":[47],"an":[48],"extension":[49],"this":[51],"approach":[52],"with":[53],"a":[54],"new":[55],"weighting":[56],"scheme":[57],"show":[59],"that":[60],"it":[61],"provides":[62],"significant":[63],"improvements":[64],"datasets":[67],"provided":[68],"task.":[72]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
