{"id":"https://openalex.org/W2100368767","doi":"https://doi.org/10.1162/coli_a_00162","title":"Generation of Compound Words in Statistical Machine Translation into Compounding Languages","display_name":"Generation of Compound Words in Statistical Machine Translation into Compounding Languages","publication_year":2013,"publication_date":"2013-04-23","ids":{"openalex":"https://openalex.org/W2100368767","doi":"https://doi.org/10.1162/coli_a_00162","mag":"2100368767"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00162","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00162","pdf_url":"https://direct.mit.edu/coli/article-pdf/39/4/1067/1802592/coli_a_00162.pdf","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":true,"oa_status":"bronze","oa_url":"https://direct.mit.edu/coli/article-pdf/39/4/1067/1802592/coli_a_00162.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051985869","display_name":"Sara Stymne","orcid":null},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sara Stymne","raw_affiliation_strings":["Uppsala University","Uppsala University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uppsala University","institution_ids":["https://openalex.org/I123387679"]},{"raw_affiliation_string":"Uppsala University ,","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004751764","display_name":"Nicola Cancedda","orcid":null},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicola Cancedda","raw_affiliation_strings":["Xerox Research Centre Europe","Xerox Research Centre Europe#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Xerox Research Centre Europe#TAB#","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067870406","display_name":"Lars Ahrenberg","orcid":null},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Lars Ahrenberg","raw_affiliation_strings":["Link\u00f6ping University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Link\u00f6ping University","institution_ids":["https://openalex.org/I102134673"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3809,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.9440965,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"39","issue":"4","first_page":"1067","last_page":"1108"},"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":0.9980999827384949,"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/T10260","display_name":"Software Engineering Research","score":0.963100016117096,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8581343293190002},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8131566643714905},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.7753472328186035},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6468384861946106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6258649230003357},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5508334040641785},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5267728567123413},{"id":"https://openalex.org/keywords/compound","display_name":"Compound","score":0.4785081446170807},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42363500595092773},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.41079992055892944},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3806186616420746},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2364935278892517},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15714138746261597}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8581343293190002},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8131566643714905},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.7753472328186035},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6468384861946106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258649230003357},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5508334040641785},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5267728567123413},{"id":"https://openalex.org/C2674912","wikidata":"https://www.wikidata.org/wiki/Q245423","display_name":"Compound","level":2,"score":0.4785081446170807},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42363500595092773},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.41079992055892944},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3806186616420746},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2364935278892517},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15714138746261597},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/coli_a_00162","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00162","pdf_url":"https://direct.mit.edu/coli/article-pdf/39/4/1067/1802592/coli_a_00162.pdf","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:DiVA.org:liu-76689","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-76689","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:6863cc42eb574643813511525c8772c7","is_oa":false,"landing_page_url":"https://doaj.org/article/6863cc42eb574643813511525c8772c7","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 39, Iss 4 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00162","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00162","pdf_url":"https://direct.mit.edu/coli/article-pdf/39/4/1067/1802592/coli_a_00162.pdf","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2100368767.pdf","grobid_xml":"https://content.openalex.org/works/W2100368767.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W129135300","https://openalex.org/W294504433","https://openalex.org/W314345615","https://openalex.org/W1480857181","https://openalex.org/W1487804284","https://openalex.org/W1492906232","https://openalex.org/W1524281572","https://openalex.org/W1535206496","https://openalex.org/W1595595359","https://openalex.org/W1631260214","https://openalex.org/W1815552937","https://openalex.org/W1819520634","https://openalex.org/W1868901511","https://openalex.org/W1966678781","https://openalex.org/W2008652694","https://openalex.org/W2015350341","https://openalex.org/W2016856586","https://openalex.org/W2018378073","https://openalex.org/W2046224275","https://openalex.org/W2054533749","https://openalex.org/W2078861931","https://openalex.org/W2080012968","https://openalex.org/W2091542740","https://openalex.org/W2098439409","https://openalex.org/W2101105183","https://openalex.org/W2105644991","https://openalex.org/W2105842272","https://openalex.org/W2113788796","https://openalex.org/W2117745860","https://openalex.org/W2119825066","https://openalex.org/W2121127625","https://openalex.org/W2123301721","https://openalex.org/W2124807415","https://openalex.org/W2125838338","https://openalex.org/W2127589427","https://openalex.org/W2128240870","https://openalex.org/W2129158994","https://openalex.org/W2132248251","https://openalex.org/W2133512280","https://openalex.org/W2134285054","https://openalex.org/W2134955506","https://openalex.org/W2139770225","https://openalex.org/W2141725067","https://openalex.org/W2142632103","https://openalex.org/W2143134347","https://openalex.org/W2144600658","https://openalex.org/W2145211186","https://openalex.org/W2146574666","https://openalex.org/W2147880316","https://openalex.org/W2155539936","https://openalex.org/W2156985047","https://openalex.org/W2158188757","https://openalex.org/W2163353449","https://openalex.org/W2164766438","https://openalex.org/W2166306133","https://openalex.org/W2169069915","https://openalex.org/W2171421863","https://openalex.org/W2276787968","https://openalex.org/W2346933546","https://openalex.org/W2531621976","https://openalex.org/W2583532397","https://openalex.org/W2591804103","https://openalex.org/W2598684926","https://openalex.org/W2604799680","https://openalex.org/W2613433911","https://openalex.org/W2616647696","https://openalex.org/W2621655723","https://openalex.org/W2913668833","https://openalex.org/W3142580018","https://openalex.org/W4205509257"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W2401723157","https://openalex.org/W2952904874","https://openalex.org/W4297690216","https://openalex.org/W1690653314","https://openalex.org/W3035316584"],"abstract_inverted_index":{"In":[0],"this":[1],"article":[2],"we":[3,182],"investigate":[4],"statistical":[5],"machine":[6,153],"translation":[7,56,94,137,168,195],"(SMT)":[8],"into":[9,112],"Germanic":[10],"languages,":[11],"with":[12,169],"a":[13,40,82,98,167],"focus":[14],"on":[15,150],"compound":[16,74,86,147],"processing.":[17],"Our":[18],"main":[19],"goal":[20],"is":[21,186],"to":[22,126,188,199],"enable":[23],"the":[24,35,49,55,63,68,93,102,117,172,177,194],"generation":[25],"of":[26,70,73,85,135],"novel":[27,164],"compounds":[28,44,89,165],"that":[29,104,106,122,184],"have":[30],"not":[31],"been":[32],"seen":[33],"in":[34,62,76,92,116,133,193,197],"training":[36,48,64],"data.":[37],"We":[38,96,140],"adopt":[39],"split-merge":[41],"strategy,":[42],"where":[43,88],"are":[45,90,110],"split":[46],"before":[47],"SMT":[50],"system,":[51],"and":[52,115,120,132,152,166],"merged":[53,109],"after":[54],"step.":[57],"This":[58],"approach":[59],"reduces":[60],"sparsity":[61],"data,":[65],"but":[66],"runs":[67],"risk":[69],"placing":[71],"translations":[72],"parts":[75],"non-consecutive":[77],"positions.":[78],"It":[79],"also":[80,141],"requires":[81],"postprocessing":[83],"step":[84],"merging,":[87,148],"reconstructed":[91],"output.":[95],"present":[97],"method":[99],"for":[100,146],"increasing":[101],"chances":[103],"components":[105],"should":[107],"be":[108],"translated":[111],"contiguous":[113],"positions":[114],"right":[118],"order":[119,198],"show":[121,183],"it":[123,185],"can":[124,162],"lead":[125],"improvements":[127],"both":[128],"by":[129],"direct":[130],"inspection":[131],"terms":[134],"standard":[136],"evaluation":[138],"metrics.":[139],"propose":[142],"several":[143],"new":[144],"methods":[145,161],"based":[149,191],"heuristics":[151],"learning,":[154],"which":[155],"outperform":[156],"previously":[157],"suggested":[158],"algorithms.":[159],"These":[160],"produce":[163],"at":[170],"least":[171],"same":[173],"overall":[174],"quality":[175],"as":[176],"baseline.":[178],"For":[179],"all":[180],"subtasks":[181],"useful":[187],"include":[189],"part-of-speech":[190],"information":[192],"process,":[196],"handle":[200],"compounds.":[201]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}