{"id":"https://openalex.org/W1989867740","doi":"https://doi.org/10.3115/1118693.1118705","title":"Extensions to HMM-based statistical word alignment models","display_name":"Extensions to HMM-based statistical word alignment models","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W1989867740","doi":"https://doi.org/10.3115/1118693.1118705","mag":"1989867740"},"language":"en","primary_location":{"id":"doi:10.3115/1118693.1118705","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118705","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118705","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing  - EMNLP '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/10.3115/1118693.1118705","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053947885","display_name":"Kristina Toutanova","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kristina Toutanova","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035796073","display_name":"H. Tolga Ilhan","orcid":"https://orcid.org/0000-0001-6793-0999"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Tolga Ilhan","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046006076","display_name":"Christopher D. Manning","orcid":"https://orcid.org/0000-0001-6155-649X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher D. Manning","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053947885"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":8.0968,"has_fulltext":true,"cited_by_count":88,"citation_normalized_percentile":{"value":0.97623616,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"10","issue":null,"first_page":"87","last_page":"94"},"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":0.9998000264167786,"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":0.9922000169754028,"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/bigram","display_name":"Bigram","score":0.9385385513305664},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.9049626588821411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.825894832611084},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7255274653434753},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6852412223815918},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6198536157608032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6193476319313049},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5562731623649597},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4808157682418823},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.42647695541381836},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34536051750183105},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07319289445877075}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9385385513305664},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9049626588821411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.825894832611084},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7255274653434753},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6852412223815918},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6198536157608032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6193476319313049},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5562731623649597},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4808157682418823},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.42647695541381836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34536051750183105},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07319289445877075},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/1118693.1118705","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118705","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118705","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing  - EMNLP '02","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.20.4181","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.4181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stanford.edu/~krist/papers/hmmalign.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.4.749","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.749","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/W/W02/W02-1012.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1118693.1118705","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118693.1118705","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118693.1118705","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL-02 conference on Empirical methods in natural language processing  - EMNLP '02","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1989867740.pdf","grobid_xml":"https://content.openalex.org/works/W1989867740.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1517947178","https://openalex.org/W1973923101","https://openalex.org/W1979102019","https://openalex.org/W2006969979","https://openalex.org/W2038698865","https://openalex.org/W2116316001","https://openalex.org/W2138753018"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W3014921584","https://openalex.org/W2169849734","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W2401728283","https://openalex.org/W2383829109","https://openalex.org/W2109126845"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"improved":[3],"HMM-based":[4],"word":[5,39],"level":[6],"alignment":[7,26,43,77],"models":[8],"for":[9,17],"statistical":[10],"machine":[11],"translation.":[12],"We":[13,45],"present":[14,46],"a":[15,64],"method":[16],"using":[18],"part":[19],"of":[20],"speech":[21],"tag":[22],"information":[23],"to":[24,31,36,63,75],"improve":[25],"accuracy,":[27],"and":[28,34,67],"an":[29,41],"approach":[30],"modeling":[32],"fertility":[33],"correspondence":[35],"the":[37,57],"empty":[38],"in":[40],"HMM":[42],"model.":[44],"accuracy":[47],"results":[48,72],"from":[49],"evaluating":[50],"Viterbi":[51],"alignments":[52,55],"against":[53],"human-judged":[54],"on":[56],"Canadian":[58],"Hansards":[59],"corpus,":[60],"as":[61],"compared":[62],"bigram":[65],"HMM,":[66],"IBM":[68],"model":[69],"4.":[70],"The":[71],"show":[73],"up":[74],"16%":[76],"error":[78],"reduction.":[79]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}