{"id":"https://openalex.org/W2163561955","doi":"https://doi.org/10.1162/coli_a_00007","title":"Learning Tractable Word Alignment Models with Complex Constraints","display_name":"Learning Tractable Word Alignment Models with Complex Constraints","publication_year":2010,"publication_date":"2010-07-27","ids":{"openalex":"https://openalex.org/W2163561955","doi":"https://doi.org/10.1162/coli_a_00007","mag":"2163561955"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00007","is_oa":false,"landing_page_url":"https://doi.org/10.1162/coli_a_00007","pdf_url":null,"source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"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/A5110724443","display_name":"Jo\u00e4o Gra\u00e7a","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jo\u00e3o V. Gra\u00e7a","raw_affiliation_strings":["L2F INESC-ID"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L2F INESC-ID","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081573359","display_name":"Kuzman Ganchev","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuzman Ganchev","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111908443","display_name":"Ben Taskar","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Taskar","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.3472,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97097264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"36","issue":"3","first_page":"481","last_page":"504"},"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":0.9998999834060669,"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":0.9966999888420105,"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":0.8664913177490234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5905306339263916},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5832063555717468},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.553360104560852},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5213354825973511},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5031859278678894},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5018770694732666},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48337072134017944},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.46514832973480225},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.4629529118537903},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44852063059806824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4397696852684021},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.43171849846839905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37734055519104004},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08202418684959412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8664913177490234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5905306339263916},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5832063555717468},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.553360104560852},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5213354825973511},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5031859278678894},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5018770694732666},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48337072134017944},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.46514832973480225},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4629529118537903},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44852063059806824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4397696852684021},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.43171849846839905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37734055519104004},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08202418684959412},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/coli_a_00007","is_oa":false,"landing_page_url":"https://doi.org/10.1162/coli_a_00007","pdf_url":null,"source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:repository.upenn.edu:grasp_papers-1068","is_oa":false,"landing_page_url":"https://repository.upenn.edu/grasp_papers/66","pdf_url":null,"source":{"id":"https://openalex.org/S4377196331","display_name":"Scholarly Commons (University of Pennsylvania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79576946","host_organization_name":"University of Pennsylvania","host_organization_lineage":["https://openalex.org/I79576946"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lab Papers (GRASP)","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.184.9184","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.184.9184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.seas.upenn.edu/%7Etaskar/pubs/cl10.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.396.4017","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.396.4017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wing.comp.nus.edu.sg/~antho/J/J10/J10-3007.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:30f5433e3a334eb485808d7e0e69e725","is_oa":false,"landing_page_url":"https://doaj.org/article/30f5433e3a334eb485808d7e0e69e725","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 36, Iss 3 (2021)","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"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":40,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W92833821","https://openalex.org/W201231365","https://openalex.org/W1551202288","https://openalex.org/W1779819959","https://openalex.org/W1973923101","https://openalex.org/W2006969979","https://openalex.org/W2008184426","https://openalex.org/W2024804623","https://openalex.org/W2030750105","https://openalex.org/W2038698865","https://openalex.org/W2049633694","https://openalex.org/W2079442239","https://openalex.org/W2098875891","https://openalex.org/W2102607778","https://openalex.org/W2106068492","https://openalex.org/W2108984739","https://openalex.org/W2110418293","https://openalex.org/W2112514265","https://openalex.org/W2115511080","https://openalex.org/W2116211107","https://openalex.org/W2116410915","https://openalex.org/W2116679574","https://openalex.org/W2124807415","https://openalex.org/W2133229022","https://openalex.org/W2134134392","https://openalex.org/W2135484641","https://openalex.org/W2137807494","https://openalex.org/W2141416357","https://openalex.org/W2143927888","https://openalex.org/W2143954309","https://openalex.org/W2151942821","https://openalex.org/W2153653739","https://openalex.org/W2156985047","https://openalex.org/W2169336678","https://openalex.org/W2169724380","https://openalex.org/W2567948266","https://openalex.org/W2798766386","https://openalex.org/W3029645440","https://openalex.org/W4205167092"],"related_works":["https://openalex.org/W2384400852","https://openalex.org/W2963259630","https://openalex.org/W3204898214","https://openalex.org/W2765271678","https://openalex.org/W2070920720","https://openalex.org/W2475062008","https://openalex.org/W2166781037","https://openalex.org/W2122294272","https://openalex.org/W2398549619","https://openalex.org/W1542743110"],"abstract_inverted_index":{"Word-level":[0],"alignment":[1,19],"of":[2,13,26,35,64,109],"bilingual":[3],"text":[4],"is":[5],"a":[6,10,21,97],"critical":[7],"resource":[8],"for":[9,17,84,113],"growing":[11],"variety":[12],"tasks.":[14],"Probabilistic":[15],"models":[16,57],"word":[18,126],"present":[20,79],"fundamental":[22],"trade-off":[23],"between":[24],"richness":[25],"captured":[27],"constraints":[28,54,95],"and":[29,33,48,73,78,88,107,133,136],"correlations":[30],"versus":[31],"efficiency":[32,63],"tractability":[34],"inference.":[36],"In":[37],"this":[38],"article,":[39],"we":[40],"use":[41],"the":[42,62,65,71],"Posterior":[43],"Regularization":[44],"framework":[45],"(Gra\u00e7a,":[46],"Ganchev,":[47],"Taskar":[49],"2007)":[50],"to":[51],"incorporate":[52],"complex":[53],"into":[55],"probabilistic":[56],"during":[58],"learning":[59,82],"without":[60],"changing":[61],"underlying":[66],"model.":[67],"We":[68,117],"focus":[69],"on":[70,121],"simple":[72],"tractable":[74],"hidden":[75],"Markov":[76],"model,":[77],"an":[80],"efficient":[81],"algorithm":[83],"incorporating":[85],"approximate":[86],"bijectivity":[87],"symmetry":[89],"constraints.":[90],"Models":[91],"estimated":[92],"with":[93],"these":[94],"produce":[96],"significant":[98],"boost":[99],"in":[100],"performance":[101],"as":[102],"measured":[103],"by":[104],"both":[105],"precision":[106],"recall":[108],"manually":[110],"annotated":[111],"alignments":[112,127],"six":[114],"language":[115],"pairs.":[116],"also":[118],"report":[119],"experiments":[120],"two":[122],"different":[123],"tasks":[124],"where":[125],"are":[128],"required:":[129],"phrase-based":[130],"machine":[131],"translation":[132],"syntax":[134],"transfer,":[135],"show":[137],"promising":[138],"improvements":[139],"over":[140],"standard":[141],"methods.":[142]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}