{"id":"https://openalex.org/W2515787481","doi":"https://doi.org/10.18653/v1/w16-2210","title":"A Framework for Discriminative Rule Selection in Hierarchical Moses","display_name":"A Framework for Discriminative Rule Selection in Hierarchical Moses","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2515787481","doi":"https://doi.org/10.18653/v1/w16-2210","mag":"2515787481"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2210","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2210","pdf_url":"https://www.aclweb.org/anthology/W16-2210.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Conference on Machine Translation: Volume 1,\n          Research Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-2210.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076127478","display_name":"Fabienne Braune","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fabienne Braune","raw_affiliation_strings":["Center for Information and Language Processing, University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing, University of Munich, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061754269","display_name":"Alexander Fraser","orcid":"https://orcid.org/0000-0003-1924-0015"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Fraser","raw_affiliation_strings":["Center for Information and Language Processing, University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing, University of Munich, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019928111","display_name":"Hal Daum\u00e9","orcid":"https://orcid.org/0000-0002-3760-345X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hal Daum\u0117 III","raw_affiliation_strings":["Computer Science and UMIACS, University of Maryland"],"affiliations":[{"raw_affiliation_string":"Computer Science and UMIACS, University of Maryland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006564889","display_name":"Ale\u0161 Tamchyna","orcid":null},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ale\u0161 Tamchyna","raw_affiliation_strings":["Charles University in Prague, Prague Czech Republic"],"affiliations":[{"raw_affiliation_string":"Charles University in Prague, Prague Czech Republic","institution_ids":["https://openalex.org/I21250087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076127478"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4417,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79396376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"92","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9894000291824341,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9664000272750854,"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/discriminative-model","display_name":"Discriminative model","score":0.8501786589622498},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6882190108299255},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6741701364517212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4663488268852234},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34599706530570984}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8501786589622498},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6882190108299255},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6741701364517212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4663488268852234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34599706530570984}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w16-2210","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2210","pdf_url":"https://www.aclweb.org/anthology/W16-2210.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Conference on Machine Translation: Volume 1,\n          Research Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2210","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2210","pdf_url":"https://www.aclweb.org/anthology/W16-2210.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Conference on Machine Translation: Volume 1,\n          Research Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6199968644","display_name":"Domain Adaptation for Statistical Machine Translation","funder_award_id":"640550","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8900516709","display_name":"Health in my Language","funder_award_id":"644402","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2515787481.pdf","grobid_xml":"https://content.openalex.org/works/W2515787481.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W5056303","https://openalex.org/W132913264","https://openalex.org/W222053410","https://openalex.org/W635530177","https://openalex.org/W1582588624","https://openalex.org/W1631260214","https://openalex.org/W1697844855","https://openalex.org/W2034639451","https://openalex.org/W2070996757","https://openalex.org/W2095669743","https://openalex.org/W2096175520","https://openalex.org/W2100281225","https://openalex.org/W2101105183","https://openalex.org/W2115081467","https://openalex.org/W2136925175","https://openalex.org/W2139183784","https://openalex.org/W2139621418","https://openalex.org/W2140133598","https://openalex.org/W2140343992","https://openalex.org/W2141440284","https://openalex.org/W2143002608","https://openalex.org/W2150378737","https://openalex.org/W2154581043","https://openalex.org/W2158917268","https://openalex.org/W2159755860","https://openalex.org/W2169954957","https://openalex.org/W2437005631","https://openalex.org/W2595715041","https://openalex.org/W3203940212"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3209574120","https://openalex.org/W3107602296","https://openalex.org/W4312192474","https://openalex.org/W4210805261","https://openalex.org/W4387297750"],"abstract_inverted_index":{"Training":[0],"discriminative":[1,69],"rule":[2,70,108,140,147],"selection":[3,109,141,148],"models":[4,28,149],"is":[5,112],"usually":[6],"expensive":[7],"because":[8],"of":[9,14,36],"the":[10,15,21,33,37],"very":[11],"large":[12,151],"size":[13],"hierarchical":[16],"grammar.":[17],"Previous":[18],"approaches":[19,76],"reduced":[20],"training":[22],"costs":[23],"either":[24],"by":[25,41],"(i)":[26,113],"using":[27],"that":[29,93,111],"are":[30,89],"local":[31],"to":[32,68,96,133,150,159],"source":[34],"side":[35],"rules":[38],"or":[39],"(ii)":[40,119],"heavily":[42],"pruning":[43],"out":[44],"negative":[45,124],"samples.":[46,125],"Moreover,":[47],"all":[48,122],"previous":[49,75],"evaluations":[50],"were":[51],"performed":[52],"on":[53,77,102,165],"small":[54],"scale":[55,146],"translation":[56,80,98,152],"tasks,":[57,104],"containing":[58],"at":[59],"most":[60],"250,000":[61],"sentence":[62],"pairs.":[63],"We":[64],"propose":[65,106],"two":[66,78],"contributions":[67],"selection.":[71],"First,":[72],"we":[73,105,144],"test":[74],"French-English":[79],"tasks":[81,153],"in":[82,163],"domains":[83],"for":[84],"which":[85],"only":[86],"limited":[87],"resources":[88],"available":[90,123],"and":[91],"show":[92],"they":[94],"fail":[95],"improve":[97,101],"quality.":[99],"To":[100],"such":[103],"a":[107],"model":[110,128],"global":[114,127],"with":[115,121],"rich":[116],"label-dependent":[117],"features":[118],"trained":[120],"Our":[126],"yields":[129],"significant":[130,161],"improvements,":[131],"up":[132],"1":[134],"BLEU":[135,164],"point,":[136],"over":[137],"previously":[138],"proposed":[139],"models.":[142],"Second,":[143],"successfully":[145],"but":[154],"have":[155],"so":[156],"far":[157],"failed":[158],"produce":[160],"improvements":[162],"these":[166],"tasks.":[167]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}