{"id":"https://openalex.org/W2291208696","doi":null,"title":"Submodularity for Data Selection in Statistical Machine Translation","display_name":"Submodularity for Data Selection in Statistical Machine Translation","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2291208696","mag":"2291208696"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.649.1204","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.649.1204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://melodi.ee.washington.edu/~bilmes/mypubs/kirchhoff2014-submodmt.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5050325468","display_name":"Katrin Kirchhoff","orcid":"https://orcid.org/0000-0002-6645-6030","observed_orcids":["https://orcid.org/0000-0002-6645-6030"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katrin Kirchhoff","raw_affiliation_strings":["University of Washington ;"],"raw_orcid":"https://orcid.org/0000-0002-6645-6030","affiliations":[{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113478221","display_name":"Jeff Bilmes","orcid":"https://orcid.org/0000-0002-7372-8778","observed_orcids":["https://orcid.org/0000-0002-7372-8778"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff Bilmes","raw_affiliation_strings":["University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":1.8519,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87670506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9771000146865845,"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":0.9771000146865845,"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":0.006800000090152025,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0020000000949949026,"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/submodular-optimization","display_name":"submodular optimization","score":0.9269999861717224},{"id":"https://openalex.org/keywords/dataset-selection","display_name":"data selection","score":0.6600000262260437},{"id":"https://openalex.org/keywords/statistical-machine-translation","display_name":"statistical machine translation","score":0.9100000262260437},{"id":"https://openalex.org/keywords/submodularity","display_name":"submodular functions","score":0.9670000076293945},{"id":"https://openalex.org/keywords/performance-guarantees","display_name":"performance guarantees","score":0.8389999866485596}],"concepts":[{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.9315125942230225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774653434753418},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6249992251396179},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6075080633163452},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5689318180084229},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4528631865978241},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.44268354773521423},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4385421574115753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4247400462627411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4012446105480194},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38555312156677246},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3439767360687256},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.19545593857765198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15166229009628296},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07636627554893494},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.649.1204","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.649.1204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://melodi.ee.washington.edu/~bilmes/mypubs/kirchhoff2014-submodmt.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.657.1002","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.657.1002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D14/D14-1014.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.672.6586","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.672.6586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://melodi.ee.washington.edu/%7Ebilmes/mypubs/kirchhoff2014-submodmt.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.675.8767","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.675.8767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://emnlp2014.org/papers/pdf/EMNLP2014014.pdf","raw_type":"text"},{"id":"mag:2291208696","doi":null,"is_oa":false,"landing_page_url":"http://emnlp2014.org/papers/pdf/EMNLP2014014.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W52746146","https://openalex.org/W222053410","https://openalex.org/W612917828","https://openalex.org/W1522553155","https://openalex.org/W1576820654","https://openalex.org/W1680189815","https://openalex.org/W1707559977","https://openalex.org/W1898824936","https://openalex.org/W1905522558","https://openalex.org/W1962684803","https://openalex.org/W2010856309","https://openalex.org/W2011193572","https://openalex.org/W2033885045","https://openalex.org/W2042932437","https://openalex.org/W2061958803","https://openalex.org/W2073110021","https://openalex.org/W2095755718","https://openalex.org/W2101309634","https://openalex.org/W2101816610","https://openalex.org/W2105410942","https://openalex.org/W2109209963","https://openalex.org/W2117278770","https://openalex.org/W2118544668","https://openalex.org/W2123318312","https://openalex.org/W2124807415","https://openalex.org/W2125536435","https://openalex.org/W2134267347","https://openalex.org/W2136477195","https://openalex.org/W2138242477","https://openalex.org/W2138597123","https://openalex.org/W2141403143","https://openalex.org/W2143996311","https://openalex.org/W2144933361","https://openalex.org/W2161943765","https://openalex.org/W2165199647","https://openalex.org/W2170735271","https://openalex.org/W2250289728","https://openalex.org/W2339504674","https://openalex.org/W2356613612","https://openalex.org/W2402118343","https://openalex.org/W2604377206","https://openalex.org/W2963241965","https://openalex.org/W3118655244","https://openalex.org/W3172695526"],"related_works":["https://openalex.org/W2251590347","https://openalex.org/W7100078521","https://openalex.org/W2218630638","https://openalex.org/W1794756993","https://openalex.org/W3004057642","https://openalex.org/W2359988089","https://openalex.org/W2773549337","https://openalex.org/W1862810382","https://openalex.org/W2904977935","https://openalex.org/W2902689991"],"abstract_inverted_index":{"We":[0,56],"introduce":[1],"submodular":[2,24,62,82],"optimization":[3],"to":[4,103,110],"the":[5,90],"problem":[6],"of":[7,61],"training":[8],"data":[9,20,94,105,112],"subset":[10],"selection":[11,21,30,95,113],"for":[12,66],"statistical":[13],"machine":[14],"translation":[15,74],"(SMT).":[16],"By":[17],"explicitly":[18],"formulating":[19],"as":[22],"a":[23,38,58],"program,":[25],"we":[26],"ob-tain":[27],"fast":[28],"scalable":[29],"algorithms":[31],"with":[32],"mathematical":[33],"performance":[34],"guarantees,":[35],"re-sulting":[36],"in":[37,115],"unified":[39],"framework":[40],"that":[41,79],"clarifies":[42],"existing":[43],"approaches":[44,53],"and":[45,50,68,107],"also":[46],"makes":[47],"both":[48],"new":[49,59],"many":[51],"previous":[52],"easily":[54,101],"accessible.":[55],"present":[57],"class":[60],"functions":[63],"designed":[64],"specifically":[65],"SMT":[67],"evaluate":[69],"them":[70],"on":[71],"two":[72],"differ-ent":[73],"tasks.":[75],"Our":[76],"results":[77],"show":[78],"our":[80,99],"best":[81],"method":[83],"significantly":[84],"outperforms":[85],"several":[86],"baseline":[87],"methods,":[88],"including":[89],"widely-used":[91],"cross-entropy":[92],"based":[93],"method.":[96],"In":[97],"addition,":[98],"approach":[100],"scales":[102],"large":[104],"sets":[106],"is":[108],"applicable":[109],"other":[111],"problems":[114],"natural":[116],"language":[117],"processing.":[118],"1":[119]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}