{"id":"https://openalex.org/W4412887868","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1020","title":"Improving Word Alignment Using Semi-Supervised Learning","display_name":"Improving Word Alignment Using Semi-Supervised Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887868","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1020"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1020","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1020","pdf_url":"https://aclanthology.org/2025.findings-acl.1020.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: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1020.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100314856","display_name":"Zhongtao Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I125934054","display_name":"National United University","ror":"https://ror.org/04twccc71","country_code":"TW","type":"education","lineage":["https://openalex.org/I125934054"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP","TW"],"is_corresponding":false,"raw_author_name":"Zhongtao Miao","raw_affiliation_strings":["The University of Tokyo , Tokyo , Japan","{miao ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo , Tokyo , Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"{miao ,","institution_ids":["https://openalex.org/I125934054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077525450","display_name":"Qiyu Wu","orcid":"https://orcid.org/0000-0002-6013-8533"},"institutions":[{"id":"https://openalex.org/I125934054","display_name":"National United University","ror":"https://ror.org/04twccc71","country_code":"TW","type":"education","lineage":["https://openalex.org/I125934054"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP","TW"],"is_corresponding":false,"raw_author_name":"Qiyu Wu","raw_affiliation_strings":["The University of Tokyo , Tokyo , Japan","{miao ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo , Tokyo , Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"{miao ,","institution_ids":["https://openalex.org/I125934054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100520423","display_name":"Masaaki Nagata","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaaki Nagata","raw_affiliation_strings":["NTT Communication Science Laboratories , NTT Corporation , Kyoto , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories , NTT Corporation , Kyoto , Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064113904","display_name":"Yoshimasa Tsuruoka","orcid":"https://orcid.org/0000-0002-0707-1077"},"institutions":[{"id":"https://openalex.org/I125934054","display_name":"National United University","ror":"https://ror.org/04twccc71","country_code":"TW","type":"education","lineage":["https://openalex.org/I125934054"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP","TW"],"is_corresponding":false,"raw_author_name":"Yoshimasa Tsuruoka","raw_affiliation_strings":["The University of Tokyo , Tokyo , Japan","{miao ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo , Tokyo , Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"{miao ,","institution_ids":["https://openalex.org/I125934054"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4204,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8075001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"19871","last_page":"19888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9796000123023987,"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":0.9796000123023987,"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/T12031","display_name":"Speech and dialogue systems","score":0.9129999876022339,"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":0.9038000106811523,"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/computer-science","display_name":"Computer science","score":0.7963765859603882},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6698811054229736},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6421327590942383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.540961742401123},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14009976387023926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7963765859603882},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6698811054229736},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6421327590942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.540961742401123},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14009976387023926},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1020","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1020","pdf_url":"https://aclanthology.org/2025.findings-acl.1020.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1020","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1020","pdf_url":"https://aclanthology.org/2025.findings-acl.1020.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887868.pdf","grobid_xml":"https://content.openalex.org/works/W4412887868.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3204019825","https://openalex.org/W2296205523"],"abstract_inverted_index":{"Word":[0],"alignment":[1,183],"plays":[2],"a":[3,86,151,169],"crucial":[4],"role":[5],"in":[6,25],"various":[7,181],"natural":[8,104],"language":[9,100,105,118,128,158],"processing":[10,106],"tasks,":[11,107],"such":[12],"as":[13,15,120],"serving":[14],"cross-lingual":[16],"signals":[17],"for":[18,35],"sentence":[19],"embedding,":[20],"reducing":[21],"hallucination":[22],"and":[23,28,47,55,78],"omission":[24],"machine":[26],"translation,":[27],"facilitating":[29],"the":[30,64,72,94,111,137,147,156,165,176],"construction":[31],"of":[32,74,89,97,113,172],"training":[33,138],"data":[34,46,51,132,141,174],"simultaneous":[36],"speech":[37],"translation.Current":[38],"state-of-theart":[39],"approaches":[40],"usually":[41],"rely":[42],"on:":[43],"(1)":[44],"supervised":[45,50],"large-scale":[48],"weakly":[49],"constructed":[52],"from":[53,71],"Wikipedia":[54],"(2)":[56],"multilingual":[57,98],"Transformer":[58],"encoder-based":[59,67],"models.However,":[60],"we":[61,79,108,149],"find":[62],"that":[63,124,164],"current":[65,177],"state-of-the-art":[66,178],"method,":[68],"BinaryAlign,":[69],"suffers":[70],"issue":[73],"insufficient":[75],"labeled":[76,131],"data,":[77],"further":[80,142],"improve":[81,155],"it":[82],"with":[83,85,130,139,168],"self-training":[84],"small":[87,170],"amount":[88,171],"parallel":[90,173],"data.In":[91],"addition,":[92],"considering":[93],"impressive":[95],"performance":[96],"large":[99,117,127,157],"models":[101,119,129],"on":[102,146,180],"many":[103],"also":[109],"explore":[110],"possibility":[112],"using":[114],"these":[115],"decoderbased":[116],"word":[121,160,182],"aligners.We":[122],"observe":[123],"although":[125],"fine-tuning":[126],"produces":[133],"acceptable":[134],"results,":[135],"augmenting":[136],"pseudo-labeled":[140],"enhances":[143],"model":[144],"performance.Based":[145],"findings,":[148],"propose":[150],"semi-supervised":[152],"framework":[153],"to":[154],"model-based":[159],"aligners.Experimental":[161],"results":[162],"demonstrate":[163],"proposed":[166],"method":[167,179],"outperforms":[175],"datasets.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}