{"id":"https://openalex.org/W2962782699","doi":"https://doi.org/10.18653/v1/p19-1144","title":"Improving Neural Language Models by Segmenting, Attending, and Predicting the Future","display_name":"Improving Neural Language Models by Segmenting, Attending, and Predicting the Future","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2962782699","doi":"https://doi.org/10.18653/v1/p19-1144","mag":"2962782699"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1144","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1144","pdf_url":"https://www.aclweb.org/anthology/P19-1144.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1144.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024338348","display_name":"Hongyin Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hongyin Luo","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA 02139, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079795665","display_name":"Lan Jiang","orcid":"https://orcid.org/0000-0002-4735-3845"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lan Jiang","raw_affiliation_strings":["School of Information Sciences, University of Illinois at Urbana-Champaign Champaign, IL 61820, USA"],"affiliations":[{"raw_affiliation_string":"School of Information Sciences, University of Illinois at Urbana-Champaign Champaign, IL 61820, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051184573","display_name":"Yonatan Belinkov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yonatan Belinkov","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA 02139, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA 02139, USA"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA 02139, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024338348"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.07532422,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82123628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1483","last_page":"1493"},"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/T13629","display_name":"Text Readability and Simplification","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/phrase","display_name":"Phrase","score":0.8643525838851929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8576592803001404},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.8227598667144775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.731567919254303},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7296655774116516},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6480159759521484},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5415021181106567},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.539147675037384},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4781692624092102},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4266645014286041},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.07555705308914185}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8643525838851929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8576592803001404},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8227598667144775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.731567919254303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7296655774116516},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6480159759521484},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5415021181106567},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.539147675037384},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4781692624092102},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4266645014286041},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.07555705308914185},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1144","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1144","pdf_url":"https://www.aclweb.org/anthology/P19-1144.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"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1144","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1144","pdf_url":"https://www.aclweb.org/anthology/P19-1144.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":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962782699.pdf","grobid_xml":"https://content.openalex.org/works/W2962782699.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W182831726","https://openalex.org/W1938755728","https://openalex.org/W2064675550","https://openalex.org/W2086161653","https://openalex.org/W2133564696","https://openalex.org/W2140679639","https://openalex.org/W2153579005","https://openalex.org/W2212703438","https://openalex.org/W2250539671","https://openalex.org/W2267186426","https://openalex.org/W2525332836","https://openalex.org/W2549416390","https://openalex.org/W2567070169","https://openalex.org/W2743945814","https://openalex.org/W2792376130","https://openalex.org/W2792764867","https://openalex.org/W2795285343","https://openalex.org/W2798569372","https://openalex.org/W2804845563","https://openalex.org/W2810075754","https://openalex.org/W2906625520","https://openalex.org/W2951104886","https://openalex.org/W2951559648","https://openalex.org/W2951672049","https://openalex.org/W2952436057","https://openalex.org/W2962746461","https://openalex.org/W2962964385","https://openalex.org/W2963073938","https://openalex.org/W2963077125","https://openalex.org/W2963266340","https://openalex.org/W2963403868","https://openalex.org/W2963411763","https://openalex.org/W2963537482","https://openalex.org/W2963631907","https://openalex.org/W2963748792","https://openalex.org/W2963754491","https://openalex.org/W2963970792","https://openalex.org/W2963983719","https://openalex.org/W2964308564","https://openalex.org/W4285719527","https://openalex.org/W4289373464","https://openalex.org/W4294170691","https://openalex.org/W4294555862","https://openalex.org/W4297788867","https://openalex.org/W4298422451","https://openalex.org/W4299838440","https://openalex.org/W4300427683","https://openalex.org/W4300687381","https://openalex.org/W4385245566"],"related_works":["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","https://openalex.org/W2787311093"],"abstract_inverted_index":{"Common":[0],"language":[1,20,80,106],"models":[2,81,119],"typically":[3],"predict":[4],"the":[5,9,26,30,54,104,134,139,142],"next":[6],"word":[7],"given":[8,27],"context.":[10],"In":[11],"this":[12],"work,":[13],"we":[14,45],"propose":[15],"a":[16,126],"method":[17,74],"that":[18,112,147],"improves":[19],"modeling":[21,107],"by":[22],"learning":[23,71],"to":[24,56,79,152],"align":[25],"context":[28],"and":[29,49,64,95,98],"following":[31],"phrase.":[32],"The":[33],"model":[34,55,114,149],"does":[35],"not":[36],"require":[37],"any":[38,159],"linguistic":[39],"annotation":[40],"of":[41,130,141],"phrase":[42,50,66,93,143],"segmentation.":[43],"Instead,":[44],"define":[46],"syntactic":[47],"heights":[48],"segmentation":[51],"rules,":[52],"enabling":[53],"automatically":[57],"induce":[58],"phrases,":[59],"recognize":[60],"their":[61],"task-specific":[62],"heads,":[63],"generate":[65],"embeddings":[67],"in":[68,103],"an":[69,87],"unsupervised":[70],"manner.":[72],"Our":[73],"can":[75],"easily":[76],"be":[77],"applied":[78],"with":[82],"different":[83,121],"network":[84],"architectures":[85],"since":[86],"independent":[88],"module":[89,145],"is":[90,101,150],"used":[91],"for":[92],"induction":[94,144],"context-phrase":[96],"alignment,":[97],"no":[99],"change":[100],"required":[102],"underlying":[105],"network.":[108],"Experiments":[109],"have":[110],"shown":[111],"our":[113,148],"outperformed":[115],"several":[116],"strong":[117],"baseline":[118],"on":[120,133],"data":[122],"sets.":[123],"We":[124],"achieved":[125],"new":[127],"state-of-the-art":[128],"performance":[129],"17.4":[131],"perplexity":[132],"Wikitext-103":[135],"dataset.":[136],"Additionally,":[137],"visualizing":[138],"outputs":[140],"showed":[146],"able":[151],"learn":[153],"approximate":[154],"phrase-level":[155],"structural":[156],"knowledge":[157],"without":[158],"annotation.":[160]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}