{"id":"https://openalex.org/W2047337702","doi":"https://doi.org/10.1017/s1351324905003931","title":"Linguistic knowledge in statistical phrase-based word alignment","display_name":"Linguistic knowledge in statistical phrase-based word alignment","publication_year":2005,"publication_date":"2005-12-06","ids":{"openalex":"https://openalex.org/W2047337702","doi":"https://doi.org/10.1017/s1351324905003931","mag":"2047337702"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324905003931","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324905003931","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-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/A5041559636","display_name":"Adri\u00e0 de Gispert","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"A. DE GISPERT","raw_affiliation_strings":["TALP Research Center, Universitat Polit\u00e8cnica de Catalunya (UPC), Jordi Girona 1-3, Campus Nord D5, 08034 Barcelona, Spain e-mail:","TALP Research Center, Universitat Polit\u00e8cnica de Catalunya (UPC), Jordi Girona 1-3, Campus Nord D5, 08034 Barcelona, Spain e-mail: agispert@gps.tsc.upc.es, canton@gps.tsc.upc.es#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TALP Research Center, Universitat Polit\u00e8cnica de Catalunya (UPC), Jordi Girona 1-3, Campus Nord D5, 08034 Barcelona, Spain e-mail:","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"TALP Research Center, Universitat Polit\u00e8cnica de Catalunya (UPC), Jordi Girona 1-3, Campus Nord D5, 08034 Barcelona, Spain e-mail: agispert@gps.tsc.upc.es, canton@gps.tsc.upc.es#TAB#","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":null,"display_name":"J. B. MARI\u00d1O","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"J. B. MARI\u00d1O","raw_affiliation_strings":["TALP Research Center, Universitat Polit\u00e8cnica de Catalunya (UPC), Jordi Girona 1-3, Campus Nord D5, 08034 Barcelona, Spain e-mail:","TALP Research Center, Universitat Polit\u00e8cnica de Catalunya (UPC), Jordi Girona 1-3, Campus Nord D5, 08034 Barcelona, Spain e-mail: agispert@gps.tsc.upc.es, canton@gps.tsc.upc.es#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TALP Research Center, Universitat Polit\u00e8cnica de Catalunya (UPC), Jordi Girona 1-3, Campus Nord D5, 08034 Barcelona, Spain e-mail:","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"TALP Research Center, Universitat Polit\u00e8cnica de Catalunya (UPC), Jordi Girona 1-3, Campus Nord D5, 08034 Barcelona, Spain e-mail: agispert@gps.tsc.upc.es, canton@gps.tsc.upc.es#TAB#","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":1.3663,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84750696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"12","issue":"1","first_page":"91","last_page":"108"},"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/T13629","display_name":"Text Readability and Simplification","score":0.9933000206947327,"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":0.8564013838768005},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.8476508855819702},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7448767423629761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6695600152015686},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6052557229995728},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5752930641174316},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4929635524749756},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.46713995933532715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3475397229194641},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3073103427886963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8564013838768005},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8476508855819702},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7448767423629761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6695600152015686},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6052557229995728},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5752930641174316},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4929635524749756},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.46713995933532715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3475397229194641},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3073103427886963},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324905003931","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324905003931","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W123309796","https://openalex.org/W161663654","https://openalex.org/W202643247","https://openalex.org/W1514141394","https://openalex.org/W1517947178","https://openalex.org/W1973923101","https://openalex.org/W1989867740","https://openalex.org/W2006969979","https://openalex.org/W2038698865","https://openalex.org/W2060953504","https://openalex.org/W2124136969","https://openalex.org/W2129765547","https://openalex.org/W2135843243","https://openalex.org/W2141532438","https://openalex.org/W2153653739","https://openalex.org/W2154384676","https://openalex.org/W2156985047","https://openalex.org/W2161792612","https://openalex.org/W3037715718","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W3011059803","https://openalex.org/W2012262991","https://openalex.org/W2384400852","https://openalex.org/W3204898214","https://openalex.org/W2963259630","https://openalex.org/W2070920720","https://openalex.org/W2398549619","https://openalex.org/W1542743110","https://openalex.org/W2532587587"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,44,51,95,134,152,159,163,171],"novel":[4],"phrase":[5,29,33,148],"alignment":[6,37,98,174,188],"strategy":[7],"combining":[8],"linguistic":[9,123,168],"knowledge":[10,169],"and":[11,31,38,56,71,102,110,141,158,178],"cooccurrence":[12,149],"measures":[13,101,150],"extracted":[14],"from":[15],"bilingual":[16],"corpora":[17],"is":[18,22],"presented.":[19],"The":[20,40,91],"algorithm":[21],"mainly":[23],"divided":[24],"into":[25],"four":[26],"steps,":[27],"namely":[28],"selection":[30],"classification,":[32],"alignment,":[34,165],"one-to-one":[35],"word":[36,97,156,173],"postprocessing.":[39],"first":[41],"stage":[42,114],"selects":[43],"linguistically-derived":[45],"set":[46],"of":[47,137,162],"phrases":[48,65,85],"that":[49,147],"convey":[50,151],"unified":[52],"meaning":[53],"during":[54],"translation":[55],"are":[57,89,126,184],"therefore":[58],"aligned":[59],"together":[60],"in":[61,170],"parallel":[62,131],"texts.":[63],"These":[64],"include":[66],"verb":[67],"phrases,":[68],"idiomatic":[69],"expressions":[70],"date":[72],"expressions.":[73],"During":[74],"the":[75,106,112,138],"second":[76],"stage,":[77],"very":[78],"high":[79],"precision":[80],"links":[81],"between":[82],"these":[83],"selected":[84],"for":[86,128],"both":[87],"languages":[88],"produced.":[90],"third":[92],"step":[93],"performs":[94],"statistical":[96,172],"using":[99],"association":[100],"link":[103],"probabilities":[104],"with":[105,133],"remaining":[107],"unaligned":[108,119],"tokens,":[109],"finally":[111],"fourth":[113],"takes":[115],"final":[116],"decisions":[117],"on":[118,122],"tokens":[120],"based":[121],"knowledge.":[124],"Experiments":[125],"reported":[127],"an":[129],"English-Spanish":[130],"corpus,":[132],"detailed":[135],"description":[136],"evaluation":[139],"measure":[140],"manual":[142],"reference":[143],"used.":[144],"Results":[145],"show":[146],"complementary":[153],"information":[154],"to":[155],"cooccurrences":[157],"stronger":[160],"evidence":[161],"correct":[164],"successfully":[166],"introducing":[167],"scheme.":[175],"Precision,":[176],"Recall":[177],"Alignment":[179],"Error":[180],"Rate":[181],"(AER)":[182],"results":[183],"presented,":[185],"outperforming":[186],"state-of-the-art":[187],"algorithms.":[189]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}