{"id":"https://openalex.org/W2787642437","doi":"https://doi.org/10.18653/v1/d18-1150","title":"Large Margin Neural Language Model","display_name":"Large Margin Neural Language Model","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2787642437","doi":"https://doi.org/10.18653/v1/d18-1150","mag":"2787642437"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1150","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1150","pdf_url":"https://www.aclweb.org/anthology/D18-1150.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1150.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082470433","display_name":"Jiaji Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiaji Huang","raw_affiliation_strings":["Baidu Research, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Baidu Research, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100421757","display_name":"Yi Li","orcid":"https://orcid.org/0000-0003-2304-5802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Li","raw_affiliation_strings":["Baidu Research, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Baidu Research, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113987537","display_name":"Wei Ping","orcid":"https://orcid.org/0000-0002-8852-6618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Ping","raw_affiliation_strings":["Baidu Research, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Baidu Research, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006404928","display_name":"Liang Huang","orcid":"https://orcid.org/0000-0001-6444-7045"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Huang","raw_affiliation_strings":["Baidu Research, Sunnyvale, CA, USA","School of EECS, Oregon State University, Corvallis, OR, USA"],"affiliations":[{"raw_affiliation_string":"Baidu Research, Sunnyvale, CA, USA","institution_ids":[]},{"raw_affiliation_string":"School of EECS, Oregon State University, Corvallis, OR, USA","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082470433"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0948,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.93125079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1183","last_page":"1191"},"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":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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9245237708091736},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.9103109240531921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8186208605766296},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7203392386436462},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6773147583007812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6568341255187988},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6165764927864075},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5399994254112244},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4759397506713867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4605153799057007},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.45205798745155334},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3767765164375305},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.062462419271469116}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9245237708091736},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.9103109240531921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186208605766296},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7203392386436462},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6773147583007812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6568341255187988},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6165764927864075},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5399994254112244},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4759397506713867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4605153799057007},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.45205798745155334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3767765164375305},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.062462419271469116},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/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/d18-1150","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1150","pdf_url":"https://www.aclweb.org/anthology/D18-1150.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/d18-1150","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1150","pdf_url":"https://www.aclweb.org/anthology/D18-1150.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":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2787642437.pdf","grobid_xml":"https://content.openalex.org/works/W2787642437.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W101286142","https://openalex.org/W179875071","https://openalex.org/W330298975","https://openalex.org/W1566877644","https://openalex.org/W1591801644","https://openalex.org/W1736701665","https://openalex.org/W1915251500","https://openalex.org/W1916559533","https://openalex.org/W1973435495","https://openalex.org/W2015840095","https://openalex.org/W2097927681","https://openalex.org/W2111305191","https://openalex.org/W2121127625","https://openalex.org/W2127141656","https://openalex.org/W2140679639","https://openalex.org/W2143166796","https://openalex.org/W2158025800","https://openalex.org/W2158148237","https://openalex.org/W2158195707","https://openalex.org/W2180952760","https://openalex.org/W2251071050","https://openalex.org/W2259472270","https://openalex.org/W2399550240","https://openalex.org/W2402268235","https://openalex.org/W2747236259","https://openalex.org/W2888779557","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963463964","https://openalex.org/W2963620441","https://openalex.org/W2963953073","https://openalex.org/W3167803720","https://openalex.org/W3211848854","https://openalex.org/W4285719527","https://openalex.org/W4327845728"],"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/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2084531783","https://openalex.org/W2020757772","https://openalex.org/W2902731467"],"abstract_inverted_index":{"We":[0],"propose":[1,42],"a":[2,43,62],"large":[3,44],"margin":[4,45,54],"criterion":[5],"for":[6,94,101],"training":[7],"neural":[8,12],"language":[9,13],"models.":[10],"Conventionally,":[11],"models":[14],"are":[15],"trained":[16,67],"by":[17],"minimizing":[18],"perplexity":[19],"(PPL)":[20],"on":[21],"grammatical":[22],"sentences.":[23],"However,":[24],"we":[25],"demonstrate":[26],"that":[27,76],"PPL":[28],"may":[29],"not":[30],"be":[31,71],"the":[32,53,56],"best":[33],"metric":[34],"to":[35,51,74,90],"optimize":[36],"in":[37,61],"some":[38],"tasks,":[39],"and":[40,58,69,97],"further":[41],"formulation.":[46],"The":[47],"proposed":[48],"method":[49,87],"aims":[50],"enlarge":[52],"between":[55],"\"good\"":[57],"\"bad\"":[59],"sentences":[60],"task-specific":[63],"sense.":[64],"It":[65],"is":[66],"end-to-end":[68],"can":[70],"widely":[72],"applied":[73],"tasks":[75],"involve":[77],"re-scoring":[78],"of":[79],"generated":[80],"text.":[81],"Compared":[82],"with":[83],"minimum-PPL":[84],"training,":[85],"our":[86],"gains":[88],"up":[89],"1.1":[91],"WER":[92],"reduction":[93],"speech":[95],"recognition":[96],"1.0":[98],"BLEU":[99],"increase":[100],"machine":[102],"translation.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}