{"id":"https://openalex.org/W2989314903","doi":"https://doi.org/10.18653/v1/w19-8672","title":"A Good Sample is Hard to Find: Noise Injection Sampling and Self-Training for Neural Language Generation Models","display_name":"A Good Sample is Hard to Find: Noise Injection Sampling and Self-Training for Neural Language Generation Models","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2989314903","doi":"https://doi.org/10.18653/v1/w19-8672","mag":"2989314903"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-8672","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-8672","pdf_url":"https://www.aclweb.org/anthology/W19-8672.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 12th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-8672.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006374446","display_name":"Chris Kedzie","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Kedzie","raw_affiliation_strings":["Columbia University Department of Computer Science","Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University Department of Computer Science","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109565051","display_name":"Kathleen McKeown","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathleen McKeown","raw_affiliation_strings":["Columbia University Department of Computer Science","Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University Department of Computer Science","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"584","last_page":"593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.8490536212921143},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6068181991577148},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.5615383982658386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5489823818206787},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5419706702232361},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5175865888595581},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5040563344955444},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4974682629108429},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.4933868944644928},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48548558354377747},{"id":"https://openalex.org/keywords/de-facto","display_name":"De facto","score":0.4785761833190918},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4771389663219452},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4395011365413666},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43889230489730835},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42363548278808594},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3828016519546509},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.32971078157424927},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22174164652824402},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1000598669052124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8490536212921143},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6068181991577148},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.5615383982658386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5489823818206787},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5419706702232361},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5175865888595581},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5040563344955444},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4974682629108429},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4933868944644928},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48548558354377747},{"id":"https://openalex.org/C2992317946","wikidata":"https://www.wikidata.org/wiki/Q712144","display_name":"De facto","level":2,"score":0.4785761833190918},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4771389663219452},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4395011365413666},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43889230489730835},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42363548278808594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3828016519546509},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32971078157424927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22174164652824402},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1000598669052124},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w19-8672","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-8672","pdf_url":"https://www.aclweb.org/anthology/W19-8672.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 12th International Conference on Natural Language Generation","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.03373","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.03373","pdf_url":"https://arxiv.org/pdf/1911.03373","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:2989314903","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.03373.pdf","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.1911.03373","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.03373","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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-8672","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-8672","pdf_url":"https://www.aclweb.org/anthology/W19-8672.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 12th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7904372578","display_name":null,"funder_award_id":"FA8650-17-C-9117","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"}],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320337349","display_name":"NIH Office of the Director","ror":"https://ror.org/00fj8a872"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2989314903.pdf","grobid_xml":"https://content.openalex.org/works/W2989314903.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W1948566616","https://openalex.org/W2054870958","https://openalex.org/W2116492379","https://openalex.org/W2124386177","https://openalex.org/W2136071191","https://openalex.org/W2157331557","https://openalex.org/W2291723583","https://openalex.org/W2353655624","https://openalex.org/W2903428882","https://openalex.org/W2914397182","https://openalex.org/W2951395840","https://openalex.org/W2962883855","https://openalex.org/W2962905474","https://openalex.org/W2963206148","https://openalex.org/W2964308564","https://openalex.org/W3105830849"],"related_works":["https://openalex.org/W2995246984","https://openalex.org/W3185447269","https://openalex.org/W2920819083","https://openalex.org/W3005915390","https://openalex.org/W2747060779","https://openalex.org/W2802184895","https://openalex.org/W2321916036","https://openalex.org/W2785994290","https://openalex.org/W2963070863","https://openalex.org/W2402448994","https://openalex.org/W3095189764","https://openalex.org/W3089287248","https://openalex.org/W2940322076","https://openalex.org/W1997873936","https://openalex.org/W3201101490","https://openalex.org/W2891539192","https://openalex.org/W2809695831","https://openalex.org/W2912117653","https://openalex.org/W2951862245","https://openalex.org/W2396251197"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNN)":[3],"are":[4,102,110],"quickly":[5],"becoming":[6],"the":[7,63,84,92],"de":[8],"facto":[9],"standard":[10],"modeling":[11],"method":[12,75],"for":[13,22,37],"many":[14],"natural":[15],"language":[16],"generation":[17],"(NLG)":[18],"tasks.":[19],"In":[20,45,66],"order":[21],"such":[23],"models":[24,98],"to":[25,58,62,76,82],"truly":[26],"be":[27,31],"useful,":[28],"they":[29],"must":[30],"capable":[32,103],"of":[33,53,104,122],"correctly":[34],"generating":[35,105],"utterances":[36,60,108],"novel":[38,78],"meaning":[39],"representations":[40],"(MRs)":[41],"at":[42],"test":[43],"time.":[44],"practice,":[46],"even":[47,95],"sophisticated":[48],"DNNs":[49],"with":[50,99],"various":[51],"forms":[52],"semantic":[54],"control":[55],"frequently":[56],"fail":[57],"generate":[59],"faithful":[61],"input":[64],"MR.":[65],"this":[67],"paper,":[68],"we":[69],"propose":[70],"an":[71],"architecture":[72],"agnostic":[73],"selftraining":[74],"sample":[77],"MR/text":[79],"utterance":[80],"pairs":[81],"augment":[83],"original":[85],"training":[86,90],"data.":[87],"Remarkably,":[88],"after":[89],"on":[91],"augmented":[93],"data,":[94],"simple":[96],"encoder-decoder":[97],"greedy":[100],"decoding":[101],"semantically":[106],"correct":[107],"that":[109],"as":[111,113],"good":[112],"state-of-the-art":[114],"outputs":[115],"in":[116],"both":[117],"automatic":[118],"and":[119],"human":[120],"evaluations":[121],"quality.":[123]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-07-26T00:00:00"}