{"id":"https://openalex.org/W3016973796","doi":"https://doi.org/10.18653/v1/2020.findings-emnlp.147","title":"SimAlign: High Quality Word Alignments Without Parallel Training Data Using Static and Contextualized Embeddings","display_name":"SimAlign: High Quality Word Alignments Without Parallel Training Data Using Static and Contextualized Embeddings","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3016973796","doi":"https://doi.org/10.18653/v1/2020.findings-emnlp.147","mag":"3016973796"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.findings-emnlp.147","doi":"https://doi.org/10.18653/v1/2020.findings-emnlp.147","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.findings-emnlp.147","pdf_url":"https://www.aclweb.org/anthology/2020.findings-emnlp.147.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":"Findings of the Association for Computational Linguistics: EMNLP 2020","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.findings-emnlp.147.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022974084","display_name":"Masoud Jalili Sabet","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Masoud Jalili Sabet","raw_affiliation_strings":["Center for Information and Language Processing (CIS) , LMU Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing (CIS) , LMU Munich , Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012225484","display_name":"Philipp Dufter","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Dufter","raw_affiliation_strings":["Center for Information and Language Processing (CIS) , LMU Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing (CIS) , LMU Munich , Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030615769","display_name":"Fran\u00e7ois Yvon","orcid":"https://orcid.org/0000-0002-7972-7442","observed_orcids":["https://orcid.org/0000-0002-7972-7442"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"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/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois Yvon","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay , CNRS , LIMSI , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay , CNRS , LIMSI , France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4210115485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071144367","display_name":"Hinrich Sch\u00fctze","orcid":"https://orcid.org/0000-0001-9514-7934","observed_orcids":["https://orcid.org/0000-0001-9514-7934"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hinrich Sch\u00fctze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3851,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.91280444,"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":"1627","last_page":"1643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9940999746322632,"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":0.9940999746322632,"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":0.004600000102072954,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.00019999999494757503,"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/word-alignment","display_name":"word alignment","score":0.9829999804496765},{"id":"https://openalex.org/keywords/contextualized-embeddings","display_name":"contextual embeddings","score":0.8730000257492065},{"id":"https://openalex.org/keywords/multilingual-word-embeddings","display_name":"multilingual embeddings","score":0.8479999899864197},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.5}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429390788078308},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7638559341430664},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7556093335151672},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7239737510681152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6352361440658569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5779748558998108},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.44815289974212646},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.43798312544822693},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09037670493125916},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2020.findings-emnlp.147","doi":"https://doi.org/10.18653/v1/2020.findings-emnlp.147","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.findings-emnlp.147","pdf_url":"https://www.aclweb.org/anthology/2020.findings-emnlp.147.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":"Findings of the Association for Computational Linguistics: EMNLP 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03013194v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-03013194","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EMNLP 2020 - Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Nov 2020, Online, United States. pp.1627 - 1643, ⟨10.18653/v1/2020.findings-emnlp.147⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.findings-emnlp.147","doi":"https://doi.org/10.18653/v1/2020.findings-emnlp.147","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.findings-emnlp.147","pdf_url":"https://www.aclweb.org/anthology/2020.findings-emnlp.147.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":"Findings of the Association for Computational Linguistics: EMNLP 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G4364068006","display_name":"Non-sequence models for tokenization replacement","funder_award_id":"740516","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3016973796.pdf","grobid_xml":"https://content.openalex.org/works/W3016973796.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W59306127","https://openalex.org/W77482081","https://openalex.org/W1480519300","https://openalex.org/W1916559533","https://openalex.org/W1973923101","https://openalex.org/W2006969979","https://openalex.org/W2016630033","https://openalex.org/W2080090262","https://openalex.org/W2100682730","https://openalex.org/W2115057736","https://openalex.org/W2121879602","https://openalex.org/W2137122906","https://openalex.org/W2137854946","https://openalex.org/W2138706636","https://openalex.org/W2138753018","https://openalex.org/W2141532438","https://openalex.org/W2148708890","https://openalex.org/W2155674569","https://openalex.org/W2156985047","https://openalex.org/W2164055961","https://openalex.org/W2222512263","https://openalex.org/W2227523508","https://openalex.org/W2250545560","https://openalex.org/W2251395256","https://openalex.org/W2270364989","https://openalex.org/W2300691323","https://openalex.org/W2401082558","https://openalex.org/W2464151748","https://openalex.org/W2469296930","https://openalex.org/W2493916176","https://openalex.org/W2507671009","https://openalex.org/W2516649778","https://openalex.org/W2520028199","https://openalex.org/W2538358357","https://openalex.org/W2564663390","https://openalex.org/W2574252446","https://openalex.org/W2611235244","https://openalex.org/W2622084140","https://openalex.org/W2757154661","https://openalex.org/W2760567570","https://openalex.org/W2798669739","https://openalex.org/W2798908575","https://openalex.org/W2803172920","https://openalex.org/W2803369080","https://openalex.org/W2890256614","https://openalex.org/W2899202004","https://openalex.org/W2912070261","https://openalex.org/W2946359678","https://openalex.org/W2946417913","https://openalex.org/W2947799968","https://openalex.org/W2952682849","https://openalex.org/W2960374072","https://openalex.org/W2962784628","https://openalex.org/W2963118869","https://openalex.org/W2963341956","https://openalex.org/W2963506925","https://openalex.org/W2963598809","https://openalex.org/W2964015966","https://openalex.org/W2964174820","https://openalex.org/W2964308564","https://openalex.org/W2965373594","https://openalex.org/W2970045405","https://openalex.org/W2970757000","https://openalex.org/W2971296520","https://openalex.org/W2971531230","https://openalex.org/W2983040767","https://openalex.org/W2987270981","https://openalex.org/W3022467813","https://openalex.org/W3032816972","https://openalex.org/W3037109418","https://openalex.org/W3088331994","https://openalex.org/W3103942011"],"related_works":["https://openalex.org/W2898767136","https://openalex.org/W2786253471","https://openalex.org/W3175595715","https://openalex.org/W2990400634","https://openalex.org/W4298129735","https://openalex.org/W2797913374","https://openalex.org/W2604275745","https://openalex.org/W2986030184","https://openalex.org/W2104907655","https://openalex.org/W4307459710"],"abstract_inverted_index":{"Word":[0],"alignments":[1,26,89],"are":[2,73,93],"useful":[3],"for":[4,95,99,125],"tasks":[5],"like":[6],"statistical":[7,109,137],"and":[8,13,38,66,97],"neural":[9],"machine":[10],"translation":[11],"(NMT)":[12],"cross-lingual":[14],"annotation":[15],"projection.Statistical":[16],"word":[17,48,62,69,121],"aligners":[18,110],"perform":[19],"well,":[20],"as":[21,41],"do":[22],"methods":[23,50],"that":[24,51,88,127],"extract":[25],"jointly":[27],"with":[28,112],"translations":[29],"in":[30],"NMT.However,":[31],"most":[32],"approaches":[33],"require":[34,52],"parallel":[35,54,83,114,142],"training":[36,43],"data,":[37],"quality":[39],"decreases":[40],"less":[42],"data":[44,77,84],"is":[45,58,128],"available.We":[46],"propose":[47],"alignment":[49,122],"no":[53],"data.The":[55],"key":[56],"idea":[57],"to":[59,104],"leverage":[60],"multilingual":[61,71],"embeddings":[63,72,92,118],"-both":[64],"static":[65],"contextualized":[67,117],"-for":[68],"alignment.Our":[70],"created":[74,90],"from":[75,91],"monolingual":[76],"only":[78],"without":[79],"relying":[80],"on":[81,140],"any":[82],"or":[85],"dictionaries.We":[86],"find":[87],"superior":[94],"four":[96],"comparable":[98],"two":[100],"language":[101],"pairs":[102],"compared":[103],"those":[105],"produced":[106],"by":[107],"traditional":[108],"-even":[111],"abundant":[113],"data;":[115],"e.g.,":[116],"achieve":[119],"a":[120,135],"F":[123],"1":[124],"English-German":[126],"5":[129],"percentage":[130],"points":[131],"higher":[132],"than":[133],"eflomal,":[134],"high-quality":[136],"aligner,":[138],"trained":[139],"100k":[141],"sentences.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}