{"id":"https://openalex.org/W2251820600","doi":"https://doi.org/10.3115/v1/e14-1001","title":"Improving Word Alignment Using Linguistic Code Switching Data","display_name":"Improving Word Alignment Using Linguistic Code Switching Data","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251820600","doi":"https://doi.org/10.3115/v1/e14-1001","mag":"2251820600"},"language":"en","primary_location":{"id":"doi:10.3115/v1/e14-1001","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/e14-1001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101488344","display_name":"Fei Huang","orcid":"https://orcid.org/0000-0002-3709-5053"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fei Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011973574","display_name":"Alexander Yates","orcid":"https://orcid.org/0000-0003-3142-5004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Yates","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101488344"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2027,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94549044,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"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":0.9997000098228455,"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/T13629","display_name":"Text Readability and Simplification","score":0.9958000183105469,"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/code-switching","display_name":"Code-switching","score":0.8505853414535522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8479630947113037},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6971544623374939},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6540773510932922},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6517238020896912},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6035551428794861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.601847231388092},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5927872061729431},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5135974884033203},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.45310303568840027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4022623300552368},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17084047198295593},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12327343225479126}],"concepts":[{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.8505853414535522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8479630947113037},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6971544623374939},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6540773510932922},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6517238020896912},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6035551428794861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.601847231388092},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5927872061729431},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5135974884033203},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.45310303568840027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4022623300552368},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17084047198295593},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12327343225479126},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/e14-1001","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/e14-1001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W8671328","https://openalex.org/W222053410","https://openalex.org/W2006969979","https://openalex.org/W2013489815","https://openalex.org/W2038698865","https://openalex.org/W2048679005","https://openalex.org/W2049633694","https://openalex.org/W2070885732","https://openalex.org/W2099534719","https://openalex.org/W2105891181","https://openalex.org/W2107628162","https://openalex.org/W2111329418","https://openalex.org/W2114569717","https://openalex.org/W2115511080","https://openalex.org/W2140702357","https://openalex.org/W2153653739","https://openalex.org/W2154368244","https://openalex.org/W2188330943","https://openalex.org/W2203920402","https://openalex.org/W2760809434","https://openalex.org/W3197026893"],"related_works":["https://openalex.org/W2771594921","https://openalex.org/W2432897346","https://openalex.org/W2181336723","https://openalex.org/W4389976243","https://openalex.org/W3158134258","https://openalex.org/W3138119129","https://openalex.org/W2940588741","https://openalex.org/W2293063924","https://openalex.org/W2974240475","https://openalex.org/W4388441038"],"abstract_inverted_index":{"Linguist":[0],"Code":[1],"Switching":[2],"(LCS)":[3],"is":[4,65,84],"a":[5,18,30,41,71,115,135,140,158],"situation":[6],"where":[7],"two":[8],"or":[9,56],"more":[10],"languages":[11],"show":[12,123],"up":[13],"in":[14,23,43,154],"the":[15,91,127],"context":[16],"of":[17,93],"single":[19],"conversation.":[20],"For":[21],"example,":[22],"EnglishChinese":[24],"code":[25,107,128],"switching,":[26],"there":[27],"might":[28],"be":[29],"sentence":[31],"like":[32],"\u201c\u00b7":[33],"\u201a15\u00a9":[34],"\u00a8":[35],"k":[36],"\u2021meeting":[37],"(We":[38],"will":[39],"have":[40],"meeting":[42],"15":[44],"minutes)\u201d.":[45],"Traditional":[46],"machine":[47],"translation":[48],"(MT)":[49],"systems":[50],"treat":[51],"LCS":[52,63,82,149],"data":[53,64,83,95,109,150],"as":[54,58],"noise,":[55],"just":[57],"regular":[59],"sentences.":[60],"However,":[61],"if":[62],"processed":[66],"intelligently,":[67],"it":[68],"can":[69,89,132],"provide":[70],"useful":[72],"signal":[73],"for":[74,96,147],"training":[75,94,119],"word":[76,116,136],"alignment":[77,117,137],"and":[78,110,139],"MT":[79,160],"models.":[80],"Moreover,":[81],"from":[85,105],"non-news":[86],"sources":[87],"which":[88],"enhance":[90],"diversity":[92],"MT.":[97],"In":[98],"this":[99,106],"paper,":[100],"we":[101,131],"first":[102],"extract":[103],"constraints":[104],"switching":[108,129],"then":[111],"incorporate":[112],"them":[113],"into":[114],"model":[118,138,142],"procedure.":[120],"We":[121],"also":[122],"that":[124],"by":[125,152],"using":[126,143,163],"data,":[130],"jointly":[133],"train":[134],"language":[141],"cotraining.":[144],"Our":[145],"techniques":[146],"incorporating":[148],"improve":[151],"2.64":[153],"BLEU":[155],"score":[156],"over":[157],"baseline":[159],"system":[161],"trained":[162],"only":[164],"standard":[165],"sentence-aligned":[166],"corpora.":[167]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}