{"id":"https://openalex.org/W2796956679","doi":"https://doi.org/10.18653/v1/n18-1137","title":"Bootstrapping Generators from Noisy Data","display_name":"Bootstrapping Generators from Noisy Data","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2796956679","doi":"https://doi.org/10.18653/v1/n18-1137","mag":"2796956679"},"language":"en","primary_location":{"id":"doi:10.18653/v1/n18-1137","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n18-1137","pdf_url":"https://www.aclweb.org/anthology/N18-1137.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 2018 Conference of the North American Chapter of\n          the Association for Computational Linguistics: Human Language\n          Technologies, Volume 1 (Long Papers)","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/N18-1137.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005336295","display_name":"Laura Perez-Beltrachini","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Laura Perez-Beltrachini","raw_affiliation_strings":["Institute for Language, Cognition and Computation School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB","University of Edinburgh,"],"affiliations":[{"raw_affiliation_string":"Institute for Language, Cognition and Computation School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041024491","display_name":"Mirella Lapata","orcid":"https://orcid.org/0000-0002-2107-1516"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mirella Lapata","raw_affiliation_strings":["Institute for Language, Cognition and Computation School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB","University of Edinburgh,"],"affiliations":[{"raw_affiliation_string":"Institute for Language, Cognition and Computation School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005336295"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.59568738,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71756008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8102699518203735},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.7777434587478638},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.660069465637207},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5949468612670898},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5537786483764648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.537737250328064},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5074922442436218},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40429016947746277},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37177878618240356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102699518203735},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.7777434587478638},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.660069465637207},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5949468612670898},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5537786483764648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.537737250328064},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5074922442436218},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40429016947746277},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37177878618240356},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.18653/v1/n18-1137","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n18-1137","pdf_url":"https://www.aclweb.org/anthology/N18-1137.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 2018 Conference of the North American Chapter of\n          the Association for Computational Linguistics: Human Language\n          Technologies, Volume 1 (Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.06385","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.06385","pdf_url":"https://arxiv.org/pdf/1804.06385","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":"","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:publications/16966526-dbb3-461d-9547-b3cdc610277a","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/16966526-dbb3-461d-9547-b3cdc610277a","pdf_url":"https://www.research.ed.ac.uk/en/publications/16966526-dbb3-461d-9547-b3cdc610277a","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Perez-Beltrachini, L & Lapata, M 2018, Bootstrapping Generators from Noisy Data. in The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. New Orleans, Louisiana , pp. 1516-1527, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, Louisiana, United States, 1/06/18. https://doi.org/10.18653/v1/N18-1137","raw_type":"contributionToPeriodical"},{"id":"mag:2796956679","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1804.06385","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":"pmh:oai:pure.ed.ac.uk:openaire/16966526-dbb3-461d-9547-b3cdc610277a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/16966526-dbb3-461d-9547-b3cdc610277a","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Perez-Beltrachini, L & Lapata, M 2018, Bootstrapping Generators from Noisy Data. in The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. New Orleans, Louisiana , pp. 1516-1527, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, Louisiana, United States, 1/06/18. https://doi.org/10.18653/v1/N18-1137","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.1804.06385","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.06385","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/n18-1137","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n18-1137","pdf_url":"https://www.aclweb.org/anthology/N18-1137.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 2018 Conference of the North American Chapter of\n          the Association for Computational Linguistics: Human Language\n          Technologies, Volume 1 (Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2796956679.pdf","grobid_xml":"https://content.openalex.org/works/W2796956679.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W27505572","https://openalex.org/W102708294","https://openalex.org/W1522301498","https://openalex.org/W1540386283","https://openalex.org/W1554039773","https://openalex.org/W1591801644","https://openalex.org/W1614862348","https://openalex.org/W1902237438","https://openalex.org/W1905882502","https://openalex.org/W1938425378","https://openalex.org/W2003170434","https://openalex.org/W2051840895","https://openalex.org/W2100833569","https://openalex.org/W2101105183","https://openalex.org/W2115221470","https://openalex.org/W2115578160","https://openalex.org/W2115641419","https://openalex.org/W2116716943","https://openalex.org/W2119717200","https://openalex.org/W2122497464","https://openalex.org/W2123442489","https://openalex.org/W2132679783","https://openalex.org/W2153443464","https://openalex.org/W2153702313","https://openalex.org/W2158681777","https://openalex.org/W2158899491","https://openalex.org/W2165075008","https://openalex.org/W2169813772","https://openalex.org/W2250539671","https://openalex.org/W2251300660","https://openalex.org/W2508885100","https://openalex.org/W2516255829","https://openalex.org/W2525907473","https://openalex.org/W2589218480","https://openalex.org/W2605243085","https://openalex.org/W2739046565","https://openalex.org/W2752442988","https://openalex.org/W2769637628","https://openalex.org/W2949447259","https://openalex.org/W2949888546","https://openalex.org/W2952523122","https://openalex.org/W2962905474","https://openalex.org/W2963091658","https://openalex.org/W2963248296","https://openalex.org/W2963498408","https://openalex.org/W2963716836","https://openalex.org/W2963842982","https://openalex.org/W2964174820","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2963415248","https://openalex.org/W2592877340","https://openalex.org/W3049690031","https://openalex.org/W2131095325","https://openalex.org/W2492652153","https://openalex.org/W3019932981","https://openalex.org/W2296841316","https://openalex.org/W3112012747","https://openalex.org/W3013503304","https://openalex.org/W3126895840","https://openalex.org/W3047616836","https://openalex.org/W2964173876","https://openalex.org/W2602938505","https://openalex.org/W3171978172","https://openalex.org/W125575914","https://openalex.org/W2991445593","https://openalex.org/W3177448563","https://openalex.org/W3124980712","https://openalex.org/W3011380190","https://openalex.org/W2346575341"],"abstract_inverted_index":{"A":[0],"core":[1],"step":[2],"in":[3,16],"statistical":[4],"data-to-text":[5],"generation":[6],"concerns":[7],"learning":[8,64],"correspondences":[9,68],"between":[10,69],"structured":[11],"data":[12,36,70],"representations":[13],"(e.g.,":[14,37,43],"facts":[15],"a":[17,56,102],"database)":[18],"and":[19,40,71,74],"associated":[20],"texts.":[21],"In":[22],"this":[23,51],"paper":[24],"we":[25],"aim":[26],"to":[27,65,81],"bootstrap":[28],"generators":[29],"from":[30],"large":[31],"scale":[32],"datasets":[33],"where":[34],"the":[35,83],"DBPedia":[38],"facts)":[39],"related":[41],"texts":[42],"Wikipedia":[44],"abstracts)":[45],"are":[46],"loosely":[47],"aligned.":[48],"We":[49,61],"tackle":[50],"challenging":[52],"task":[53],"by":[54],"introducing":[55],"special-purpose":[57],"content":[58,84],"selection":[59],"mechanism.":[60],"use":[62],"multi-instance":[63],"automatically":[66],"discover":[67],"text":[72],"pairs":[73],"show":[75],"how":[76],"these":[77],"can":[78],"be":[79],"used":[80],"enhance":[82],"signal":[85],"while":[86],"training":[87],"an":[88],"encoder-decoder":[89,104],"architecture.":[90],"Experimental":[91],"results":[92],"demonstrate":[93],"that":[94],"models":[95],"trained":[96],"with":[97],"content-specific":[98],"objectives":[99],"improve":[100],"upon":[101],"vanilla":[103],"which":[105],"solely":[106],"relies":[107],"on":[108],"soft":[109],"attention.":[110]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}