{"id":"https://openalex.org/W2948359020","doi":"https://doi.org/10.18653/v1/p19-1596","title":"Curate and Generate: A Corpus and Method for Joint Control of Semantics and Style in Neural NLG","display_name":"Curate and Generate: A Corpus and Method for Joint Control of Semantics and Style in Neural NLG","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2948359020","doi":"https://doi.org/10.18653/v1/p19-1596","mag":"2948359020"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1596","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1596","pdf_url":"https://www.aclweb.org/anthology/P19-1596.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1596.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089287500","display_name":"Shereen Oraby","orcid":null},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shereen Oraby","raw_affiliation_strings":["Natural Language and Dialog Systems Lab University of California, Santa Cruz","UNIVERSITY OF CALIFORNIA (SANTA CRUZ)"],"affiliations":[{"raw_affiliation_string":"Natural Language and Dialog Systems Lab University of California, Santa Cruz","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"UNIVERSITY OF CALIFORNIA (SANTA CRUZ)","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019893567","display_name":"Vrindavan Harrison","orcid":null},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vrindavan Harrison","raw_affiliation_strings":["Natural Language and Dialog Systems Lab University of California, Santa Cruz","UNIVERSITY OF CALIFORNIA (SANTA CRUZ)"],"affiliations":[{"raw_affiliation_string":"Natural Language and Dialog Systems Lab University of California, Santa Cruz","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"UNIVERSITY OF CALIFORNIA (SANTA CRUZ)","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012722031","display_name":"Abteen Ebrahimi","orcid":null},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abteen Ebrahimi","raw_affiliation_strings":["Natural Language and Dialog Systems Lab University of California, Santa Cruz","UNIVERSITY OF CALIFORNIA (SANTA CRUZ)"],"affiliations":[{"raw_affiliation_string":"Natural Language and Dialog Systems Lab University of California, Santa Cruz","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"UNIVERSITY OF CALIFORNIA (SANTA CRUZ)","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102868325","display_name":"Marilyn Walker","orcid":"https://orcid.org/0000-0003-3306-6439"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marilyn Walker","raw_affiliation_strings":["Natural Language and Dialog Systems Lab University of California, Santa Cruz","UNIVERSITY OF CALIFORNIA (SANTA CRUZ)"],"affiliations":[{"raw_affiliation_string":"Natural Language and Dialog Systems Lab University of California, Santa Cruz","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"UNIVERSITY OF CALIFORNIA (SANTA CRUZ)","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089287500"],"corresponding_institution_ids":["https://openalex.org/I185103710"],"apc_list":null,"apc_paid":null,"fwci":0.46085324,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70220277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5938","last_page":"5951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/markup-language","display_name":"Markup language","score":0.8706260919570923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.784768283367157},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.6759824752807617},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6495708227157593},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.636239230632782},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.6033810377120972},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5590866804122925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.555109977722168},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5441920757293701},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4247454106807709},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32671308517456055},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.24781087040901184},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09998703002929688},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09884867072105408},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09585699439048767},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.09347349405288696},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.058612972497940063}],"concepts":[{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.8706260919570923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784768283367157},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.6759824752807617},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6495708227157593},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.636239230632782},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.6033810377120972},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5590866804122925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.555109977722168},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5441920757293701},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4247454106807709},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32671308517456055},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.24781087040901184},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09998703002929688},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09884867072105408},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09585699439048767},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.09347349405288696},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.058612972497940063},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p19-1596","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1596","pdf_url":"https://www.aclweb.org/anthology/P19-1596.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.01334","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.01334","pdf_url":"https://arxiv.org/pdf/1906.01334","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2948359020","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.01334","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1906.01334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.01334","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1596","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1596","pdf_url":"https://www.aclweb.org/anthology/P19-1596.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948359020.pdf","grobid_xml":"https://content.openalex.org/works/W2948359020.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W2676019","https://openalex.org/W1533861849","https://openalex.org/W1536586776","https://openalex.org/W1902237438","https://openalex.org/W1948566616","https://openalex.org/W2044523681","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2096783683","https://openalex.org/W2126385423","https://openalex.org/W2130942839","https://openalex.org/W2147002563","https://openalex.org/W2149837184","https://openalex.org/W2161699319","https://openalex.org/W2250539671","https://openalex.org/W2250861254","https://openalex.org/W2251939518","https://openalex.org/W2252123671","https://openalex.org/W2291723583","https://openalex.org/W2467834614","https://openalex.org/W2578330760","https://openalex.org/W2739874095","https://openalex.org/W2786913767","https://openalex.org/W2891732163","https://openalex.org/W2892024358","https://openalex.org/W2935206035","https://openalex.org/W2949413855","https://openalex.org/W2962788902","https://openalex.org/W2962801572","https://openalex.org/W2962805889","https://openalex.org/W2962905474","https://openalex.org/W2963018534","https://openalex.org/W2963366196","https://openalex.org/W2963912046","https://openalex.org/W2964008635","https://openalex.org/W2964098600","https://openalex.org/W2964222296","https://openalex.org/W2964308564","https://openalex.org/W2964321064","https://openalex.org/W2977923675"],"related_works":["https://openalex.org/W2951113489","https://openalex.org/W3116836881","https://openalex.org/W2907452027","https://openalex.org/W2949413855","https://openalex.org/W3106356412","https://openalex.org/W2963267809","https://openalex.org/W2151691130","https://openalex.org/W1794039122","https://openalex.org/W3157109131","https://openalex.org/W228150076","https://openalex.org/W2096831027","https://openalex.org/W2965451813","https://openalex.org/W2142327972","https://openalex.org/W1596986901","https://openalex.org/W3116934019","https://openalex.org/W168804263","https://openalex.org/W2962739339","https://openalex.org/W2791431914","https://openalex.org/W3088644109","https://openalex.org/W2738134019"],"abstract_inverted_index":{"Neural":[0],"natural":[1],"language":[2],"generation":[3],"(NNLG)":[4],"from":[5,94],"structured":[6],"meaning":[7,82,131],"representations":[8,83,132],"has":[9],"become":[10],"increasingly":[11],"popular":[12],"in":[13,68],"recent":[14],"years.":[15],"While":[16],"we":[17],"have":[18],"seen":[19],"progress":[20],"with":[21,87],"generating":[22],"syntactically":[23],"correct":[24],"utterances":[25],"that":[26,148,163],"preserve":[27],"semantics,":[28],"various":[29],"shortcomings":[30],"of":[31,80,113,118,127,172],"NNLG":[32,69],"systems":[33],"are":[34,53],"clear:":[35],"new":[36,39],"tasks":[37],"require":[38],"training":[40,78],"data":[41,93],"which":[42],"is":[43],"not":[44],"available":[45,96],"or":[46],"straightforward":[47],"to":[48,153,181],"acquire,":[49],"and":[50,55,59,84,97,102,115,133,143,176],"model":[51,120],"outputs":[52],"simple":[54],"may":[56],"be":[57,150],"dull":[58],"repetitive.":[60],"This":[61],"paper":[62],"addresses":[63],"these":[64],"two":[65],"critical":[66],"challenges":[67],"by:":[70],"(1)":[71],"scalably":[72,151],"(and":[73],"at":[74],"no":[75],"cost)":[76],"creating":[77],"datasets":[79,156],"parallel":[81,130],"reference":[85,137],"texts":[86,138],"rich":[88],"style":[89,108,185],"markup":[90,109],"by":[91],"using":[92],"freely":[95],"naturally":[98],"descriptive":[99],"user":[100],"reviews,":[101],"(2)":[103],"systematically":[104],"exploring":[105],"how":[106],"the":[107,164,179],"enables":[110],"joint":[111],"control":[112,166],"semantic":[114],"stylistic":[116],"aspects":[117],"neural":[119],"output.":[121],"We":[122],"present":[123],"YelpNLG,":[124],"a":[125,145],"corpus":[126],"300,000":[128],"rich,":[129],"highly":[134],"stylistically":[135],"varied":[136],"spanning":[139],"different":[140],"restaurant":[141],"attributes,":[142],"describe":[144],"novel":[146],"methodology":[147],"can":[149],"reused":[152],"generate":[154],"NLG":[155],"for":[157],"other":[158],"domains.":[159],"The":[160],"experiments":[161],"show":[162],"models":[165,180],"important":[167],"aspects,":[168],"including":[169],"lexical":[170],"choice":[171],"adjectives,":[173],"output":[174],"length,":[175],"sentiment,":[177],"allowing":[178],"successfully":[182],"hit":[183],"multiple":[184],"targets":[186],"without":[187],"sacrificing":[188],"semantics.":[189]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}