{"id":"https://openalex.org/W2963972328","doi":"https://doi.org/10.18653/v1/d18-1153","title":"Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling","display_name":"Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2963972328","doi":"https://doi.org/10.18653/v1/d18-1153","mag":"2963972328"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1153","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1153","pdf_url":"https://www.aclweb.org/anthology/D18-1153.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 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/D18-1153.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100657035","display_name":"Liyuan Liu","orcid":"https://orcid.org/0000-0003-2585-323X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"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":"Liyuan Liu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Southern California, Los Angeles, CA, USA","***University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009408707","display_name":"Xiang Ren","orcid":"https://orcid.org/0000-0001-8655-663X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Ren","raw_affiliation_strings":["University  of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039500313","display_name":"Jingbo Shang","orcid":"https://orcid.org/0000-0002-7249-4404"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"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":"Jingbo Shang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Southern California, Los Angeles, CA, USA","***University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102325476","display_name":"Xiaotao Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"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":"Xiaotao Gu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Southern California, Los Angeles, CA, USA","***University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061177999","display_name":"Jian Peng","orcid":"https://orcid.org/0000-0002-1736-2978"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"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"]},{"id":"https://openalex.org/I16820183","display_name":"Illinois College","ror":"https://ror.org/02ys5x139","country_code":"US","type":"education","lineage":["https://openalex.org/I16820183"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Peng","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Southern California, Los Angeles, CA, USA","Carle Illinois College of Medicine; National Center for Supercomputing Applications (NCSA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Carle Illinois College of Medicine; National Center for Supercomputing Applications (NCSA)","institution_ids":["https://openalex.org/I4210135837","https://openalex.org/I16820183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"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":"Jiawei Han","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Southern California, Los Angeles, CA, USA","Information Trust Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Information Trust Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1215","last_page":"1225"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.8456202745437622},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.615436851978302},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5640827417373657},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5525069236755371},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5414867401123047},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.528683602809906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5240129232406616},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5031968951225281},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48815399408340454},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4543168246746063},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44108280539512634},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1256985068321228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456202745437622},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.615436851978302},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5640827417373657},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5525069236755371},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5414867401123047},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.528683602809906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5240129232406616},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5031968951225281},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48815399408340454},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4543168246746063},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44108280539512634},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1256985068321228},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1153","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1153","pdf_url":"https://www.aclweb.org/anthology/D18-1153.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 on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1153","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1153","pdf_url":"https://www.aclweb.org/anthology/D18-1153.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 on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5176188519","display_name":null,"funder_award_id":"Cooperative Agreement Number W911NF-09-2-0053 (the","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G948678646","display_name":null,"funder_award_id":"W911NF-09-2-0053","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963972328.pdf","grobid_xml":"https://content.openalex.org/works/W2963972328.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1486649854","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1539309091","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2004763266","https://openalex.org/W2098921539","https://openalex.org/W2144578941","https://openalex.org/W2160236242","https://openalex.org/W2170973209","https://openalex.org/W2259472270","https://openalex.org/W2296283641","https://openalex.org/W2302255633","https://openalex.org/W2319920447","https://openalex.org/W2519314406","https://openalex.org/W2524428287","https://openalex.org/W2549416390","https://openalex.org/W2574163994","https://openalex.org/W2581624817","https://openalex.org/W2606347107","https://openalex.org/W2611669587","https://openalex.org/W2739034105","https://openalex.org/W2756381707","https://openalex.org/W2764043458","https://openalex.org/W2769137120","https://openalex.org/W2951299559","https://openalex.org/W2952087486","https://openalex.org/W2952729433","https://openalex.org/W2962676330","https://openalex.org/W2962739339","https://openalex.org/W2962902328","https://openalex.org/W2962964385","https://openalex.org/W2963000224","https://openalex.org/W2963034893","https://openalex.org/W2963446712","https://openalex.org/W2963563735","https://openalex.org/W2963625095","https://openalex.org/W2963674932","https://openalex.org/W2963703075","https://openalex.org/W2963706742","https://openalex.org/W2963748792","https://openalex.org/W2963839582","https://openalex.org/W2963983719","https://openalex.org/W2964118293","https://openalex.org/W2964121744","https://openalex.org/W3099701504","https://openalex.org/W4293718192","https://openalex.org/W4294344649","https://openalex.org/W4294555862","https://openalex.org/W4300427683"],"related_works":["https://openalex.org/W2373300491","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W1998810860","https://openalex.org/W4206442282","https://openalex.org/W2384505857","https://openalex.org/W2355171581","https://openalex.org/W2145253956","https://openalex.org/W1212596013"],"abstract_inverted_index":{"Many":[0],"efforts":[1],"have":[2],"been":[3],"made":[4],"to":[5,20,76,86,130],"facilitate":[6],"natural":[7],"language":[8,13],"processing":[9],"tasks":[10],"with":[11,84,141],"pre-trained":[12],"models":[14],"(LMs),":[15],"and":[16,30,124,127,133],"brought":[17],"significant":[18],"improvements":[19],"various":[21],"applications.":[22,72],"To":[23],"fully":[24],"leverage":[25],"the":[26,58,94,113,153],"nearly":[27],"unlimited":[28],"corpora":[29],"capture":[31],"linguistic":[32],"information":[33,50,83],"of":[34,48,93,155],"multifarious":[35],"levels,":[36],"large-size":[37],"LMs":[38,79,129,138],"are":[39,51,139],"required;":[40],"but":[41],"for":[42,70,105,144],"a":[43,87,101],"specific":[44,88],"task,":[45],"only":[46],"parts":[47],"these":[49],"useful.":[52],"Such":[53],"large-sized":[54],"LMs,":[55],"even":[56],"in":[57],"inference":[59],"stage,":[60],"may":[61],"cause":[62],"heavy":[63],"computation":[64],"workloads,":[65],"making":[66],"them":[67],"too":[68],"time-consuming":[69],"large-scale":[71],"Here":[73],"we":[74,99,116],"propose":[75],"compress":[77],"bulky":[78],"while":[80],"preserving":[81],"useful":[82],"regard":[85],"task.":[89],"As":[90],"different":[91,97],"layers":[92],"model":[95,106,136],"keep":[96],"information,":[98],"develop":[100],"layer":[102,120],"selection":[103],"method":[104],"pruning":[107],"using":[108],"sparsityinducing":[109],"regularization.":[110],"By":[111],"introducing":[112],"dense":[114],"connectivity,":[115],"can":[117],"detach":[118],"any":[119],"without":[121],"affecting":[122],"others,":[123],"stretch":[125],"shallow":[126],"wide":[128],"be":[131],"deep":[132],"narrow.":[134],"In":[135],"training,":[137],"learned":[140],"layerwise":[142],"dropouts":[143],"better":[145],"robustness.":[146],"Experiments":[147],"on":[148],"two":[149],"benchmark":[150],"datasets":[151],"demonstrate":[152],"effectiveness":[154],"our":[156],"method.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}