{"id":"https://openalex.org/W2076977565","doi":"https://doi.org/10.3115/1073083.1073151","title":"Using similarity scoring to improve the bilingual dictionary for word alignment","display_name":"Using similarity scoring to improve the bilingual dictionary for word alignment","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2076977565","doi":"https://doi.org/10.3115/1073083.1073151","mag":"2076977565"},"language":"en","primary_location":{"id":"doi:10.3115/1073083.1073151","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073151","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073151","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073151","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079357303","display_name":"Katharina Probst","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Katharina Probst","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006856255","display_name":"Ralf D. Brown","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ralf Brown","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079357303"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.0911,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84267331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"409","last_page":"409"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9976000189781189,"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":0.8253318071365356},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.781575083732605},{"id":"https://openalex.org/keywords/bilingual-dictionary","display_name":"Bilingual dictionary","score":0.7143557071685791},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6795295476913452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6627516746520996},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6401715874671936},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5275123715400696},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.48294466733932495},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4192246198654175},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13466504216194153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253318071365356},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.781575083732605},{"id":"https://openalex.org/C2779235283","wikidata":"https://www.wikidata.org/wiki/Q2640207","display_name":"Bilingual dictionary","level":2,"score":0.7143557071685791},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6795295476913452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6627516746520996},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6401715874671936},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5275123715400696},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.48294466733932495},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4192246198654175},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13466504216194153},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1073083.1073151","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073151","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073151","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.8442","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.8442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P02/P02-1052.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1073083.1073151","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073151","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073151","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2076977565.pdf","grobid_xml":"https://content.openalex.org/works/W2076977565.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1574901103","https://openalex.org/W1587546825","https://openalex.org/W1971165323","https://openalex.org/W2006969979","https://openalex.org/W2008495066","https://openalex.org/W2097333193","https://openalex.org/W2138753018","https://openalex.org/W2138787466","https://openalex.org/W2138961427","https://openalex.org/W2167684316","https://openalex.org/W2210151373","https://openalex.org/W3147241436","https://openalex.org/W4242019303"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2118758177","https://openalex.org/W4330338194","https://openalex.org/W2153520307","https://openalex.org/W2151459719","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2002275558","https://openalex.org/W4206274156"],"abstract_inverted_index":{"We":[0,29],"describe":[1],"an":[2,41],"approach":[3,42],"to":[4,43],"improve":[5],"the":[6,18,25,35,50,72,96],"bilingual":[7,51],"cooccurrence":[8,65],"dictionary":[9,20,52],"that":[10],"is":[11,99],"used":[12],"for":[13,92],"word":[14,70,78,93],"alignment,":[15],"and":[16,39,60,90],"evaluate":[17],"improved":[19,97],"using":[21],"a":[22,31,58,63,68,85],"version":[23],"of":[24],"Competitive":[26,36],"Linking":[27,37],"algorithm.":[28],"demonstrate":[30],"problem":[32],"faced":[33],"by":[34,53],"algorithm":[38],"present":[40],"ameliorate":[44],"it.":[45],"In":[46],"particular,":[47],"we":[48],"rebuild":[49],"clustering":[54],"similar":[55],"words":[56],"in":[57,71,88],"language":[59,74],"assigning":[61],"them":[62],"higher":[64],"score":[66],"with":[67],"given":[69],"other":[73],"than":[75],"each":[76],"single":[77],"would":[79],"have":[80],"otherwise.":[81],"Experimental":[82],"results":[83],"show":[84],"significant":[86],"improvement":[87],"precision":[89],"recall":[91],"alignment":[94],"when":[95],"dicitonary":[98],"used.":[100]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}