{"id":"https://openalex.org/W2250771647","doi":"https://doi.org/10.18653/v1/w15-2507","title":"A Proposal for a Coherence Corpus in Machine Translation","display_name":"A Proposal for a Coherence Corpus in Machine Translation","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250771647","doi":"https://doi.org/10.18653/v1/w15-2507","mag":"2250771647"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-2507","is_oa":true,"landing_page_url":"http://doi.org/10.18653/v1/w15-2507","pdf_url":"https://doi.org/10.18653/v1/w15-2507","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Discourse in Machine Translation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/w15-2507","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103227420","display_name":"Karin Smith","orcid":"https://orcid.org/0000-0002-2926-2771"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Karin Sim Smith","raw_affiliation_strings":["University of Sheffield#N#"],"affiliations":[{"raw_affiliation_string":"University of Sheffield#N#","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074142241","display_name":"Wilker Aziz","orcid":"https://orcid.org/0000-0002-2093-3866"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wilker Aziz","raw_affiliation_strings":["University of Sheffield#N#"],"affiliations":[{"raw_affiliation_string":"University of Sheffield#N#","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053217291","display_name":"Lucia Specia","orcid":"https://orcid.org/0000-0002-5495-3128"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lucia Specia","raw_affiliation_strings":["University of Amsterdam"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103227420"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":2.5887,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.91742859,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"58"},"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":0.9991999864578247,"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":0.9941999912261963,"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/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.86100172996521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7544974088668823},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6504358053207397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.608234167098999},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5246334671974182},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4732387959957123},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45127880573272705},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4454098641872406},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3219638466835022},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07994550466537476},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07584187388420105},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0556524395942688}],"concepts":[{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.86100172996521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544974088668823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6504358053207397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.608234167098999},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5246334671974182},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4732387959957123},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45127880573272705},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4454098641872406},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3219638466835022},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07994550466537476},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07584187388420105},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0556524395942688},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w15-2507","is_oa":true,"landing_page_url":"http://doi.org/10.18653/v1/w15-2507","pdf_url":"https://doi.org/10.18653/v1/w15-2507","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Discourse in Machine Translation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-2507","is_oa":true,"landing_page_url":"http://doi.org/10.18653/v1/w15-2507","pdf_url":"https://doi.org/10.18653/v1/w15-2507","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Discourse in Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250771647.pdf","grobid_xml":"https://content.openalex.org/works/W2250771647.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W41621595","https://openalex.org/W91670896","https://openalex.org/W112038384","https://openalex.org/W203948990","https://openalex.org/W255975419","https://openalex.org/W1614298861","https://openalex.org/W1728737950","https://openalex.org/W2083778102","https://openalex.org/W2101566153","https://openalex.org/W2104658712","https://openalex.org/W2105850947","https://openalex.org/W2108786706","https://openalex.org/W2123388068","https://openalex.org/W2123849094","https://openalex.org/W2133330855","https://openalex.org/W2140646431","https://openalex.org/W2140676672","https://openalex.org/W2141895568","https://openalex.org/W2151996595","https://openalex.org/W2152052831","https://openalex.org/W2159426623","https://openalex.org/W2160131015","https://openalex.org/W2162429782","https://openalex.org/W2163038970","https://openalex.org/W2166545452","https://openalex.org/W2167702024","https://openalex.org/W2182920187","https://openalex.org/W2248607539","https://openalex.org/W2250761393","https://openalex.org/W2250952041","https://openalex.org/W2251356693","https://openalex.org/W2251796964","https://openalex.org/W2251804000","https://openalex.org/W2251994258","https://openalex.org/W2252000648","https://openalex.org/W2252093523","https://openalex.org/W2252147974","https://openalex.org/W2270190199","https://openalex.org/W2331726854","https://openalex.org/W2399346130"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165"],"abstract_inverted_index":{"Coherence":[0],"in":[1,18,20,69,91,107,117],"Machine":[2],"Translation":[3],"(MT)":[4],"has":[5],"received":[6],"little":[7],"attention":[8],"to":[9,56,62,76,85],"date.":[10],"One":[11],"of":[12,26,67,81,88],"the":[13,24,45],"main":[14],"issues":[15,66],"we":[16],"face":[17],"work":[19],"this":[21],"area":[22],"is":[23],"lack":[25],"labelled":[27],"data.":[28],"While":[29],"coherent":[30],"(human":[31],"authored)":[32],"texts":[33,38],"are":[34,52],"abundant":[35],"and":[36,64,109],"incoherent":[37],"could":[39,97],"be":[40,99],"taken":[41],"from":[42],"MT":[43,92],"output,":[44],"latter":[46],"also":[47],"contains":[48],"other":[49],"errors":[50,87],"which":[51],"not":[53],"specifically":[54],"related":[55],"coherence.":[57],"This":[58],"makes":[59],"it":[60],"difficult":[61],"identify":[63],"quantify":[65],"coherence":[68,89,105,115],"those":[70],"texts.":[71],"We":[72],"introduce":[73],"an":[74],"initiative":[75],"create":[77],"a":[78,95,102],"corpus":[79,96],"consisting":[80],"data":[82,113],"artificially":[83],"manipulated":[84],"contain":[86],"common":[90],"output.":[93],"Such":[94],"then":[98],"used":[100],"as":[101,111],"benchmark":[103],"for":[104,114],"models":[106,116],"MT,":[108],"potentially":[110],"training":[112],"supervised":[118],"settings.":[119]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}