{"id":"https://openalex.org/W2053705431","doi":"https://doi.org/10.1145/1008992.1009043","title":"Learning phonetic similarity for matching named entity translations and mining new translations","display_name":"Learning phonetic similarity for matching named entity translations and mining new translations","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W2053705431","doi":"https://doi.org/10.1145/1008992.1009043","mag":"2053705431"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5111426224","display_name":"Wai Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wai Lam","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044103045","display_name":"Ruizhang Huang","orcid":"https://orcid.org/0000-0002-8941-3914"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruizhang Huang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055182705","display_name":"Pik-Shan Cheung","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pik-Shan Cheung","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111426224"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":3.2863,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92311495,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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":0.998199999332428,"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":0.9973000288009644,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8503168821334839},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7155758142471313},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6876776814460754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6848427057266235},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6283860206604004},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5661342740058899},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.5078464150428772},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.49878954887390137},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4653421640396118},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4645874798297882},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.44666725397109985},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3539801836013794},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.1448211371898651},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10499811172485352},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.059270888566970825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8503168821334839},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7155758142471313},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6876776814460754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6848427057266235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6283860206604004},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5661342740058899},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.5078464150428772},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.49878954887390137},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4653421640396118},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4645874798297882},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.44666725397109985},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3539801836013794},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.1448211371898651},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10499811172485352},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.059270888566970825},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1008992.1009043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W71111251","https://openalex.org/W1515938884","https://openalex.org/W1535810436","https://openalex.org/W1549114989","https://openalex.org/W1597409757","https://openalex.org/W1977545325","https://openalex.org/W2006426911","https://openalex.org/W2024181699","https://openalex.org/W2032571942","https://openalex.org/W2069317438","https://openalex.org/W2102749417","https://openalex.org/W2150071570","https://openalex.org/W2222512263","https://openalex.org/W4255492838","https://openalex.org/W6630747237","https://openalex.org/W6992951189"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W2155874911","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W2032007337","https://openalex.org/W3000685722","https://openalex.org/W1884363728","https://openalex.org/W4253099099","https://openalex.org/W4386977977","https://openalex.org/W4200491110"],"abstract_inverted_index":{"We":[0,38],"propose":[1],"a":[2,27,67],"novel":[3],"named":[4,60,74],"entity":[5,61,75],"matching":[6,16,29,62],"model":[7,30],"which":[8,31],"considers":[9],"both":[10],"semantic":[11],"and":[12],"phonetic":[13,28],"clues.":[14],"The":[15],"is":[17,26,96],"formulated":[18],"as":[19],"an":[20,91],"optimization":[21],"problem.":[22],"One":[23],"major":[24],"component":[25],"exploits":[32],"similarity":[33,46],"at":[34],"the":[35,45,106],"phoneme":[36,50],"level.":[37],"investigate":[39],"three":[40],"learning":[41],"algorithms":[42],"for":[43,70],"obtaining":[44],"information":[47],"of":[48],"basic":[49],"units":[51],"based":[52],"on":[53],"training":[54],"examples.":[55],"By":[56],"applying":[57],"this":[58],"proposed":[59],"model,":[63],"we":[64],"also":[65],"develop":[66],"mining":[68],"framework":[69,83],"discovering":[71],"new,":[72],"unseen":[73],"translations":[76,102],"from":[77],"online":[78],"daily":[79],"Web":[80],"news.":[81],"This":[82],"harvests":[84],"comparable":[85],"news":[86],"in":[87,105],"different":[88],"languages":[89],"using":[90],"existing":[92],"bilingual":[93],"dictionary.":[94,107],"It":[95],"able":[97],"to":[98],"discover":[99],"new":[100],"name":[101],"not":[103],"found":[104]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}