{"id":"https://openalex.org/W3011520178","doi":"https://doi.org/10.1109/ialp48816.2019.9037662","title":"Exploring Context\u2019s Diversity to Improve Neural Language Model","display_name":"Exploring Context\u2019s Diversity to Improve Neural Language Model","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011520178","doi":"https://doi.org/10.1109/ialp48816.2019.9037662","mag":"3011520178"},"language":"en","primary_location":{"id":"doi:10.1109/ialp48816.2019.9037662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp48816.2019.9037662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049750015","display_name":"Yanchun Zhang","orcid":"https://orcid.org/0000-0002-5094-5980"},"institutions":[{"id":"https://openalex.org/I102345215","display_name":"Xihua University","ror":"https://ror.org/04gwtvf26","country_code":"CN","type":"education","lineage":["https://openalex.org/I102345215"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanchun Zhang","raw_affiliation_strings":["School of Computer and Software Engineering, Xihua University Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Software Engineering, Xihua University Chengdu, China","institution_ids":["https://openalex.org/I102345215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066358713","display_name":"Xingyuan Chen","orcid":"https://orcid.org/0000-0002-9061-6524"},"institutions":[{"id":"https://openalex.org/I2802584641","display_name":"Leshan Normal University","ror":"https://ror.org/036cvz290","country_code":"CN","type":"education","lineage":["https://openalex.org/I2802584641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyuan Chen","raw_affiliation_strings":["School of Computer Science, Leshan Normal University, Leshan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Leshan Normal University, Leshan, China","institution_ids":["https://openalex.org/I2802584641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043790437","display_name":"Peng Jin","orcid":"https://orcid.org/0000-0002-4835-0312"},"institutions":[{"id":"https://openalex.org/I2802584641","display_name":"Leshan Normal University","ror":"https://ror.org/036cvz290","country_code":"CN","type":"education","lineage":["https://openalex.org/I2802584641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Jin","raw_affiliation_strings":["School of Computer Science, Leshan Normal University, Leshan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Leshan Normal University, Leshan, China","institution_ids":["https://openalex.org/I2802584641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087562798","display_name":"Yajun Du","orcid":"https://orcid.org/0000-0001-5999-6699"},"institutions":[{"id":"https://openalex.org/I102345215","display_name":"Xihua University","ror":"https://ror.org/04gwtvf26","country_code":"CN","type":"education","lineage":["https://openalex.org/I102345215"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yajun Du","raw_affiliation_strings":["School of Computer and Software Engineering, Xihua University Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Software Engineering, Xihua University Chengdu, China","institution_ids":["https://openalex.org/I102345215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs 1602 6291","issue":null,"first_page":"419","last_page":"423"},"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":0.9998000264167786,"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":0.9965999722480774,"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/softmax-function","display_name":"Softmax function","score":0.9247580766677856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6972066164016724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5573832392692566},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5522149801254272},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5272680521011353},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5239577293395996},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5205160975456238},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5060111880302429},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.4589371085166931},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45706242322921753},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45636624097824097},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45458683371543884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38461142778396606},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.381820410490036},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.3705323338508606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1942516565322876}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9247580766677856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6972066164016724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5573832392692566},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5522149801254272},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5272680521011353},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5239577293395996},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5205160975456238},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5060111880302429},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.4589371085166931},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45706242322921753},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45636624097824097},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45458683371543884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38461142778396606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.381820410490036},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3705323338508606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1942516565322876},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp48816.2019.9037662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp48816.2019.9037662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W35527955","https://openalex.org/W179875071","https://openalex.org/W1591801644","https://openalex.org/W1632114991","https://openalex.org/W1999965501","https://openalex.org/W2064675550","https://openalex.org/W2132339004","https://openalex.org/W2133564696","https://openalex.org/W2158195707","https://openalex.org/W2275625487","https://openalex.org/W2342395274","https://openalex.org/W2472952455","https://openalex.org/W2474824677","https://openalex.org/W2514588627","https://openalex.org/W2519224033","https://openalex.org/W2766712968","https://openalex.org/W2784621220","https://openalex.org/W2896457183","https://openalex.org/W2952409498","https://openalex.org/W2953029503","https://openalex.org/W2963077125","https://openalex.org/W2963248348","https://openalex.org/W2963341956","https://openalex.org/W2963524349","https://openalex.org/W2963625095","https://openalex.org/W2964308564","https://openalex.org/W4285719527","https://openalex.org/W6600213771","https://openalex.org/W6601425427","https://openalex.org/W6635446068","https://openalex.org/W6694627246","https://openalex.org/W6720877245","https://openalex.org/W6744415713","https://openalex.org/W6747855403","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W4367154275","https://openalex.org/W2913125146","https://openalex.org/W2911303748","https://openalex.org/W4391307109","https://openalex.org/W4225630782","https://openalex.org/W4310030444","https://openalex.org/W4380994319","https://openalex.org/W4389157492","https://openalex.org/W4287163743","https://openalex.org/W3207800728"],"abstract_inverted_index":{"The":[0,72],"neural":[1],"language":[2],"models":[3],"(NLMs),":[4],"such":[5],"as":[6,66],"long":[7],"short":[8],"term":[9],"memery":[10],"networks":[11],"(LSTMs),":[12],"have":[13],"achieved":[14],"great":[15],"success":[16],"over":[17],"the":[18,21,29,33,38,63,85,101,127,131,141,150,155,175,179,188],"years.":[19],"However":[20],"NLMs":[22],"usually":[23],"only":[24],"minimize":[25],"a":[26,55,81,96,117],"loss":[27,120,129],"between":[28],"prediction":[30,159],"results":[31,103,180],"and":[32],"target":[34,86],"words.":[35],"In":[36],"fact,":[37],"context":[39],"has":[40],"natural":[41,64],"diversity,":[42,74,152],"i.e.":[43],"there":[44,79],"are":[45,93],"few":[46],"words":[47,87],"that":[48,84],"could":[49,147],"occur":[50],"more":[51],"than":[52],"once":[53],"in":[54,69,75],"certain":[56],"length":[57],"of":[58,104,130,158,181],"word":[59],"sequence.":[60,99],"We":[61],"report":[62],"diversity":[65,68],"context's":[67,73,151],"this":[70,113],"paper.":[71],"our":[76,145,182],"model,":[77],"means":[78],"is":[80,123,170,177],"high":[82],"probability":[83],"predicted":[88],"by":[89,172],"any":[90,105,135],"two":[91,106,136,165],"contexts":[92,107],"different":[94,137],"given":[95,138],"fixed":[97],"input":[98],"Namely":[100],"softmax":[102,132],"should":[108],"be":[109],"diverse.":[110],"Based":[111,163],"on":[112,164,187],"observation,":[114],"we":[115],"propose":[116],"new":[118,142],"cross-entropy":[119,128,143],"function":[121],"which":[122],"used":[124],"to":[125],"calculate":[126],"outputs":[133],"for":[134,160],"contexts.":[139],"Adding":[140],"loss,":[144],"approach":[146],"explicitly":[148],"consider":[149],"therefore":[153],"improving":[154],"model's":[156],"sensitivity":[157],"every":[161],"context.":[162],"typical":[166],"LSTM":[167],"models,":[168],"one":[169],"regularized":[171],"dropout":[173],"while":[174],"other":[176],"not,":[178],"experiment":[183],"show":[184],"its":[185],"effectiveness":[186],"benchmark":[189],"dataset.":[190]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}