{"id":"https://openalex.org/W1928693685","doi":"https://doi.org/10.18653/v1/d15-1107","title":"Auto-Sizing Neural Networks: With Applications to n-gram Language Models","display_name":"Auto-Sizing Neural Networks: With Applications to n-gram Language Models","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1928693685","doi":"https://doi.org/10.18653/v1/d15-1107","mag":"1928693685"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d15-1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1107","pdf_url":"https://www.aclweb.org/anthology/D15-1107.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 2015 Conference on Empirical Methods in Natural Language Processing","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/D15-1107.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005840801","display_name":"Kenton Murray","orcid":"https://orcid.org/0000-0002-5628-1003"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenton Murray","raw_affiliation_strings":["Department of Computer Science and Engineering University of Notre Dame","University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame","institution_ids":[]},{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036026526","display_name":"David Chiang","orcid":"https://orcid.org/0000-0002-0435-4864"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Chiang","raw_affiliation_strings":["Department of Computer Science and Engineering University of Notre Dame","University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame","institution_ids":[]},{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"908","last_page":"916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.995199978351593,"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/perplexity","display_name":"Perplexity","score":0.9075915813446045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8231034278869629},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7758556604385376},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6664234399795532},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6534736156463623},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5717299580574036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5509669780731201},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5346637964248657},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5130240321159363},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.43179452419281006},{"id":"https://openalex.org/keywords/sizing","display_name":"Sizing","score":0.4144282639026642},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08387267589569092}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9075915813446045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8231034278869629},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7758556604385376},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6664234399795532},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6534736156463623},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5717299580574036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5509669780731201},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5346637964248657},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5130240321159363},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43179452419281006},{"id":"https://openalex.org/C2777767291","wikidata":"https://www.wikidata.org/wiki/Q1080291","display_name":"Sizing","level":2,"score":0.4144282639026642},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08387267589569092},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d15-1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1107","pdf_url":"https://www.aclweb.org/anthology/D15-1107.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d15-1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1107","pdf_url":"https://www.aclweb.org/anthology/D15-1107.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1928693685.pdf","grobid_xml":"https://content.openalex.org/works/W1928693685.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W932413789","https://openalex.org/W1508567213","https://openalex.org/W1665214252","https://openalex.org/W1978259121","https://openalex.org/W1985258458","https://openalex.org/W2047092297","https://openalex.org/W2089745520","https://openalex.org/W2093545205","https://openalex.org/W2095705004","https://openalex.org/W2114766824","https://openalex.org/W2120861206","https://openalex.org/W2124807415","https://openalex.org/W2151687858","https://openalex.org/W2156297475","https://openalex.org/W2164301055","https://openalex.org/W2251682575","https://openalex.org/W2474824677","https://openalex.org/W2595715041","https://openalex.org/W2913535645","https://openalex.org/W2998704965","https://openalex.org/W3012264151","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2084531783","https://openalex.org/W2902731467"],"abstract_inverted_index":{"Neural":[0],"networks":[1],"have":[2],"been":[3],"shown":[4],"to":[5,25,28,72,79],"improve":[6],"performance":[7],"across":[8],"a":[9,51,96],"range":[10],"of":[11,39,44,84,111],"natural-language":[12],"tasks.":[13],"However,":[14],"designing":[15],"and":[16,65,75,100],"training":[17],"them":[18],"can":[19],"be":[20],"complicated.":[21],"Frequently,":[22],"researchers":[23],"resort":[24],"repeated":[26],"experimentation":[27],"pick":[29],"optimal":[30],"settings.":[31],"In":[32],"this":[33,70],"paper,":[34],"we":[35],"address":[36],"the":[37,41,82,108],"issue":[38],"choosing":[40],"correct":[42],"number":[43,83],"units":[45,62,86],"in":[46,95],"hidden":[47,61,85],"layers.":[48],"We":[49,68,90],"introduce":[50],"method":[52,71],"for":[53],"automatically":[54],"adjusting":[55],"network":[56],"size":[57],"by":[58],"pruning":[59],"out":[60],"through":[63],",1":[64],"2,1":[66],"regularization.":[67],"apply":[69],"language":[73],"modeling":[74],"demonstrate":[76],"its":[77],"ability":[78],"correctly":[80],"choose":[81],"while":[87],"maintaining":[88],"perplexity.":[89],"also":[91],"include":[92],"these":[93,103],"models":[94,106],"machine":[97],"translation":[98],"decoder":[99],"show":[101],"that":[102],"smaller":[104],"neural":[105],"maintain":[107],"significant":[109],"improvements":[110],"their":[112],"unpruned":[113],"versions.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}