{"id":"https://openalex.org/W2050690204","doi":"https://doi.org/10.1109/ialp.2014.6973501","title":"Extracting parallel phrases from comparable corpora","display_name":"Extracting parallel phrases from comparable corpora","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2050690204","doi":"https://doi.org/10.1109/ialp.2014.6973501","mag":"2050690204"},"language":"en","primary_location":{"id":"doi:10.1109/ialp.2014.6973501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2014.6973501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Asian Language Processing (IALP)","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/A5063283510","display_name":"Jiexin Zhang","orcid":"https://orcid.org/0009-0003-5488-9386"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiexin Zhang","raw_affiliation_strings":["School of Cornputer Science and Technology Harbin Institute of Technology Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Cornputer Science and Technology Harbin Institute of Technology Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040038124","display_name":"Hailong Cao","orcid":"https://orcid.org/0000-0002-6842-8674"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Cao","raw_affiliation_strings":["School of Cornputer Science and Technology Harbin Institute of Technology Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Cornputer Science and Technology Harbin Institute of Technology Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101661008","display_name":"Tiejun Zhao","orcid":"https://orcid.org/0000-0003-4659-4935"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Zhao","raw_affiliation_strings":["School of Cornputer Science and Technology Harbin Institute of Technology Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Cornputer Science and Technology Harbin Institute of Technology Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063283510"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.08775612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"166","last_page":"169"},"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":0.9990000128746033,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9742000102996826,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8535047173500061},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.8229818344116211},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7532692551612854},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7178646326065063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6871397495269775},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6136676073074341},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.5401574373245239},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5374959111213684},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43842801451683044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4012411832809448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8535047173500061},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8229818344116211},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7532692551612854},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7178646326065063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6871397495269775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6136676073074341},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.5401574373245239},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5374959111213684},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43842801451683044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4012411832809448}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp.2014.6973501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2014.6973501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W75158669","https://openalex.org/W1979102019","https://openalex.org/W2006969979","https://openalex.org/W2041232209","https://openalex.org/W2102749417","https://openalex.org/W2107695330","https://openalex.org/W2112900913","https://openalex.org/W2121415745","https://openalex.org/W2121745180","https://openalex.org/W2124807415","https://openalex.org/W2140406733","https://openalex.org/W2140903445","https://openalex.org/W2250357620","https://openalex.org/W2437005631","https://openalex.org/W6602963042","https://openalex.org/W6660569965","https://openalex.org/W6676989195","https://openalex.org/W6678282225","https://openalex.org/W6680859986","https://openalex.org/W6691368049"],"related_works":["https://openalex.org/W2384400852","https://openalex.org/W3204898214","https://openalex.org/W2963259630","https://openalex.org/W4240926580","https://openalex.org/W2070920720","https://openalex.org/W2122294272","https://openalex.org/W2398549619","https://openalex.org/W1542743110","https://openalex.org/W2786253471","https://openalex.org/W3175595715"],"abstract_inverted_index":{"The":[0,74,106],"state-of-the-art":[1,124],"statistical":[2],"machine":[3],"translation":[4,81],"models":[5],"are":[6,69],"trained":[7],"with":[8,25,130],"the":[9,13,37,48,55,66,80,89,92,101,109,117,120,140],"parallel":[10,71,133],"corpora.":[11],"However,":[12],"traditional":[14],"SMT":[15,125],"loses":[16],"its":[17],"power":[18],"when":[19],"it":[20],"comes":[21],"to":[22],"language":[23],"pairs":[24,53,68],"few":[26],"bilingual":[27],"resources.":[28],"This":[29],"paper":[30],"proposes":[31],"a":[32,41,60,123,131],"novel":[33],"method":[34],"that":[35,88],"treats":[36],"phrase":[38,52,67],"extraction":[39],"as":[40],"classification":[42],"task.":[43],"We":[44],"first":[45],"automatically":[46],"generate":[47],"training":[49],"and":[50,100],"testing":[51],"for":[54],"classifier.":[56],"Then,":[57],"we":[58],"train":[59],"SVM":[61],"classifier":[62,93],"which":[63,127],"can":[64],"determine":[65],"either":[70],"or":[72],"non-parallel.":[73],"proposed":[75],"approach":[76],"is":[77,97,103,112,128],"evaluated":[78,114],"on":[79,94,119],"task":[82],"of":[83,91,108,122],"Chinese-English.":[84],"Experimental":[85],"results":[86,138],"show":[87],"precision":[90],"test":[95],"sets":[96],"above":[98,104],"70%":[99],"accuracy":[102],"98%":[105],"quality":[107],"extracted":[110],"data":[111],"also":[113],"by":[115],"measuring":[116],"impact":[118],"performance":[121],"system,":[126],"built":[129],"small":[132],"corpus.":[134],"It":[135],"shows":[136],"better":[137],"over":[139],"baseline":[141],"system.":[142]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}