{"id":"https://openalex.org/W2903357770","doi":"https://doi.org/10.18653/v1/w18-6310","title":"Improving Neural Language Models with Weight Norm Initialization and Regularization","display_name":"Improving Neural Language Models with Weight Norm Initialization and Regularization","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2903357770","doi":"https://doi.org/10.18653/v1/w18-6310","mag":"2903357770"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6310","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6310","pdf_url":"https://www.aclweb.org/anthology/W18-6310.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 Third Conference on Machine Translation: Research Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-6310.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010730319","display_name":"Christian Herold","orcid":"https://orcid.org/0000-0001-7097-2057"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christian Herold","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046577673","display_name":"Yingbo Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yingbo Gao","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010730319"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.6767,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78530833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"100"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9908000230789185,"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/treebank","display_name":"Treebank","score":0.9038834571838379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995954513549805},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6755058765411377},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6563330888748169},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5526201128959656},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5261449813842773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49375662207603455},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.477792352437973},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.45342350006103516},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4437016546726227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4335739016532898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40422284603118896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3830574154853821},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22941482067108154}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9038834571838379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995954513549805},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6755058765411377},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6563330888748169},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5526201128959656},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5261449813842773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49375662207603455},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.477792352437973},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.45342350006103516},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4437016546726227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4335739016532898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40422284603118896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3830574154853821},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22941482067108154},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-6310","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6310","pdf_url":"https://www.aclweb.org/anthology/W18-6310.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 Third Conference on Machine Translation: Research Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6310","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6310","pdf_url":"https://www.aclweb.org/anthology/W18-6310.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 Third Conference on Machine Translation: Research Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7366229540","display_name":"A Sequence Classification Framework for Human Language Technology","funder_award_id":"694537","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903357770.pdf","grobid_xml":"https://content.openalex.org/works/W2903357770.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1591801644","https://openalex.org/W1934041838","https://openalex.org/W1938755728","https://openalex.org/W1970689298","https://openalex.org/W1999965501","https://openalex.org/W2064675550","https://openalex.org/W2086161653","https://openalex.org/W2134237567","https://openalex.org/W2144513243","https://openalex.org/W2212703438","https://openalex.org/W2251640092","https://openalex.org/W2265902746","https://openalex.org/W2284050935","https://openalex.org/W2408727897","https://openalex.org/W2525332836","https://openalex.org/W2549416390","https://openalex.org/W2553303224","https://openalex.org/W2571859396","https://openalex.org/W2742448943","https://openalex.org/W2743945814","https://openalex.org/W2757047188","https://openalex.org/W2758605572","https://openalex.org/W2951559648","https://openalex.org/W2951672049","https://openalex.org/W2962964385","https://openalex.org/W2963266340","https://openalex.org/W2963347649","https://openalex.org/W2963374479","https://openalex.org/W2963403868","https://openalex.org/W2963537482","https://openalex.org/W2963685250","https://openalex.org/W2963748792","https://openalex.org/W2963938518","https://openalex.org/W2963983719","https://openalex.org/W2998704965","https://openalex.org/W4285719527","https://openalex.org/W4294555862","https://openalex.org/W4298422451","https://openalex.org/W4299838440","https://openalex.org/W4300427683","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2740662036","https://openalex.org/W3142119062","https://openalex.org/W159209093","https://openalex.org/W589103562","https://openalex.org/W1991220724","https://openalex.org/W2251234095","https://openalex.org/W2964047924","https://openalex.org/W3150294986","https://openalex.org/W4299838440","https://openalex.org/W2962832505"],"abstract_inverted_index":{"Embedding":[0],"and":[1,33,120],"projection":[2],"matrices":[3,28],"are":[4,43,87,97],"commonly":[5],"used":[6],"in":[7,15,29,71],"neural":[8],"language":[9,31,106],"models":[10,32],"(NLM)":[11],"as":[12,14],"well":[13],"other":[16,64],"sequence":[17],"processing":[18],"networks":[19],"that":[20,35,51],"operate":[21],"on":[22,103,116,125],"large":[23],"vocabularies.":[24],"We":[25,49,76],"examine":[26],"such":[27],"fine-tuned":[30],"observe":[34],"a":[36,79,90],"NLM":[37],"learns":[38],"word":[39,47,60],"vectors":[40],"whose":[41,85],"norms":[42,56],"related":[44],"to":[45,99,114,123],"the":[46,54],"frequencies.":[48],"show":[50],"by":[52],"initializing":[53],"weight":[55,80],"with":[57,63],"scaled":[58],"log":[59],"counts,":[61],"together":[62],"techniques,":[65],"lower":[66],"perplexities":[67,102],"can":[68],"be":[69],"obtained":[70],"early":[72],"epochs":[73],"of":[74],"training.":[75],"also":[77],"introduce":[78],"norm":[81],"regularization":[82],"loss":[83],"term,":[84],"hyperparameters":[86],"tuned":[88],"via":[89],"grid":[91],"search.":[92],"With":[93],"this":[94],"method,":[95],"we":[96],"able":[98],"significantly":[100],"improve":[101],"two":[104],"word-level":[105],"modeling":[107],"tasks":[108],"(without":[109],"dynamic":[110],"evaluation):":[111],"from":[112,121],"54.44":[113],"53.16":[115],"Penn":[117],"Treebank":[118],"(PTB)":[119],"61.45":[122],"60.13":[124],"WikiText-2":[126],"(WT2).":[127]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}