{"id":"https://openalex.org/W142179422","doi":"https://doi.org/10.21437/interspeech.2006-350","title":"Linguistic tuple segmentation in n-gram-based statistical machine translation","display_name":"Linguistic tuple segmentation in n-gram-based statistical machine translation","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W142179422","doi":"https://doi.org/10.21437/interspeech.2006-350","mag":"142179422"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-350","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},"type":"conference-paper","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adri\u00e0 de Gispert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063420793","display_name":"Jos\u00e9 Bernardo Mari\u00f1o Acebal","orcid":"https://orcid.org/0000-0002-9471-8675"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jos\u00e9 B. Mari\u00f1o","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2443,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.40965265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"paper 1049","last_page":"Tue2CaP.1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9573000073432922,"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/machine-translation","display_name":"Machine translation","score":0.8133503198623657},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6990146636962891},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6955547332763672},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6712561249732971},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6317715644836426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.628950834274292},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.47406715154647827},{"id":"https://openalex.org/keywords/language-translation","display_name":"Language translation","score":0.4459218382835388},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.38634395599365234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33656102418899536},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16023126244544983},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.13987308740615845}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8133503198623657},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6990146636962891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955547332763672},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6712561249732971},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6317715644836426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.628950834274292},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.47406715154647827},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.4459218382835388},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38634395599365234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33656102418899536},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16023126244544983},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.13987308740615845},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2006-350","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.944.310","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.944.310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nlp.lsi.upc.edu/papers/gispert06.pdf","raw_type":"text"},{"id":"pmh:oai:generic.eprints.org:366243","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/366243/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"","raw_type":"Conference or Workshop Item"},{"id":"mag:142179422","is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/interspeech/interspeech2006.html#GispertM06","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Conference of the International Speech Communication Association","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2276267953","https://openalex.org/W2381460974","https://openalex.org/W2369209412","https://openalex.org/W3138258020","https://openalex.org/W857367634","https://openalex.org/W2977662398","https://openalex.org/W2179715610","https://openalex.org/W1908323313","https://openalex.org/W3177823748","https://openalex.org/W2742676644","https://openalex.org/W2233156216","https://openalex.org/W2095907708","https://openalex.org/W1579252010","https://openalex.org/W104489331","https://openalex.org/W3113828716","https://openalex.org/W2167283987","https://openalex.org/W2114478103","https://openalex.org/W59198652","https://openalex.org/W2725592455","https://openalex.org/W2001566447"],"abstract_inverted_index":{"Ngram-based":[0],"Statistical":[1],"Machine":[2],"Translation":[3],"relies":[4],"on":[5,36],"a":[6,24,33,40,71,113],"standard":[7],"Ngram":[8],"language":[9],"model":[10,22],"of":[11,26,74,83,108],"tuples":[12],"to":[13],"estimate":[14],"the":[15,57,79,84,106],"translation":[16,21],"pro-cess.":[17],"In":[18,66,105],"training,":[19],"this":[20,53,61,67,75,109],"requires":[23],"segmentation":[25,38,115],"each":[27,82],"parallel":[28],"sentence,":[29],"which":[30,117],"involves":[31],"taking":[32],"hard":[34,62],"decision":[35,63],"tuple":[37,135],"when":[39,52],"word":[41,46,54],"is":[42,49,64],"not":[43],"linked":[44],"during":[45],"align-ment.":[47],"This":[48],"especially":[50],"critical":[51],"appears":[55],"in":[56,87,123],"target":[58],"language,":[59],"as":[60],"compulsory.":[65],"paper":[68],"we":[69,111],"present":[70,112],"thorough":[72],"study":[73],"situation,":[76],"comparing":[77],"for":[78],"rst":[80],"time":[81],"proposed":[85],"techniques":[86],"two":[88],"independent":[89],"tasks,":[90],"namely":[91],"EnglishSpanish":[92],"European":[93],"Parlia-ment":[94],"Proceedings":[95],"large-vocabulary":[96],"task":[97],"and":[98],"ArabicEnglish":[99],"Basic":[100],"Travel":[101],"Expressions":[102],"small-data":[103],"task.":[104],"face":[107],"comparison,":[110],"novel":[114],"technique":[116],"incorporates":[118],"lin-guistic":[119],"information.":[120],"Results":[121],"obtained":[122],"both":[124],"tasks":[125],"outperform":[126],"all":[127],"previous":[128],"techniques.":[129],"Index":[130],"Terms:":[131],"statistical":[132],"machine":[133],"translation,":[134],"segmentation,":[136],"n-gram-based":[137],"SMT,":[138],"linguistic":[139],"information":[140]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
