{"id":"https://openalex.org/W2885771996","doi":"https://doi.org/10.18653/v1/p18-3002","title":"Sampling Informative Training Data for RNN Language Models","display_name":"Sampling Informative Training Data for RNN Language Models","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2885771996","doi":"https://doi.org/10.18653/v1/p18-3002","mag":"2885771996"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-3002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-3002","pdf_url":"https://www.aclweb.org/anthology/P18-3002.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 ACL 2018, Student Research Workshop","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-3002.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040910395","display_name":"Jared Fernandez","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jared Fernandez","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science Northwestern University Evanston, IL 60208"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science Northwestern University Evanston, IL 60208","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043450042","display_name":"Doug Downey","orcid":"https://orcid.org/0000-0002-4737-8444"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Doug Downey","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science Northwestern University Evanston, IL 60208"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science Northwestern University Evanston, IL 60208","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"13"},"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":0.9998000264167786,"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":0.9925000071525574,"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/perplexity","display_name":"Perplexity","score":0.9903392791748047},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.8298464417457581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8219295740127563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6755963563919067},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6639915704727173},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6620675325393677},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6250141859054565},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5555885434150696},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49876952171325684},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.47008776664733887},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45755162835121155},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44805479049682617},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4374054968357086},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4220000207424164},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40377485752105713},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07989072799682617},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.07063046097755432},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06156134605407715}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9903392791748047},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.8298464417457581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8219295740127563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6755963563919067},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6639915704727173},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6620675325393677},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6250141859054565},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5555885434150696},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49876952171325684},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.47008776664733887},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45755162835121155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44805479049682617},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4374054968357086},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4220000207424164},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40377485752105713},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07989072799682617},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.07063046097755432},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06156134605407715},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-3002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-3002","pdf_url":"https://www.aclweb.org/anthology/P18-3002.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 ACL 2018, Student Research Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-3002","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-3002","pdf_url":"https://www.aclweb.org/anthology/P18-3002.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 ACL 2018, Student Research Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2214144720","display_name":"2018 Association for Computational Linguistics (ACL) Student Workshop","funder_award_id":"1827830","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4531480098","display_name":"CAREER: Web Information Extraction: Integration and Scaling","funder_award_id":"1351029","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309475","display_name":"Northwestern University","ror":"https://ror.org/000e0be47"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2885771996.pdf","grobid_xml":"https://content.openalex.org/works/W2885771996.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W115367774","https://openalex.org/W179875071","https://openalex.org/W1522301498","https://openalex.org/W1631260214","https://openalex.org/W1842094663","https://openalex.org/W1934041838","https://openalex.org/W2064675550","https://openalex.org/W2107878390","https://openalex.org/W2117278770","https://openalex.org/W2134800885","https://openalex.org/W2157331557","https://openalex.org/W2162287622","https://openalex.org/W2177410802","https://openalex.org/W2525332836","https://openalex.org/W2567070169","https://openalex.org/W2605203995","https://openalex.org/W2611669587","https://openalex.org/W2794302998","https://openalex.org/W2963748792","https://openalex.org/W2963970792","https://openalex.org/W2964121744","https://openalex.org/W4294635920","https://openalex.org/W4298422451","https://openalex.org/W4300092207","https://openalex.org/W4300427683"],"related_works":["https://openalex.org/W2610308580","https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W4287323699","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467"],"abstract_inverted_index":{"We":[0,43,58],"propose":[1],"an":[2,37],"unsupervised":[3],"importance":[4,55],"sampling":[5,56],"approach":[6,28,70],"to":[7],"selecting":[8],"training":[9,25],"data":[10,65],"for":[11],"recurrent":[12],"neural":[13],"network":[14],"(RNN)":[15],"language":[16,41,61],"models.":[17],"To":[18],"increase":[19],"the":[20,24,46,80],"information":[21],"content":[22],"of":[23,49,78],"set,":[26],"our":[27,53,68],"preferentially":[29],"samples":[30],"high":[31],"perplexity":[32,48],"sentences,":[33],"as":[34],"determined":[35],"by":[36],"easily":[38],"queryable":[39],"n-gram":[40],"model.":[42],"experimentally":[44],"evaluate":[45],"heldout":[47],"models":[50,62,72],"trained":[51,63,73],"with":[52],"various":[54],"distributions.":[57],"show":[59],"that":[60],"on":[64],"sampled":[66,76],"using":[67],"proposed":[69],"outperform":[71],"over":[74],"randomly":[75],"subsets":[77],"both":[79],"Billion":[81],"Word":[82]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}