{"id":"https://openalex.org/W2911665948","doi":"https://doi.org/10.18653/v1/w18-5428","title":"Interpreting Word-Level Hidden State Behaviour of Character-Level LSTM Language Models","display_name":"Interpreting Word-Level Hidden State Behaviour of Character-Level LSTM Language Models","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2911665948","doi":"https://doi.org/10.18653/v1/w18-5428","mag":"2911665948"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-5428","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5428","pdf_url":"https://www.aclweb.org/anthology/W18-5428.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 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-5428.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030352549","display_name":"Avery Hiebert","orcid":null},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Avery Hiebert","raw_affiliation_strings":["Department of Computer Science, University of Victoria, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081999133","display_name":"Cole Peterson","orcid":null},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cole Peterson","raw_affiliation_strings":["Department of Computer Science, University of Victoria, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085831385","display_name":"Alona Fyshe","orcid":"https://orcid.org/0000-0003-4367-0306"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alona Fyshe","raw_affiliation_strings":["Computing Science / Psychology Departments, University of Alberta, Canada"],"affiliations":[{"raw_affiliation_string":"Computing Science / Psychology Departments, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030863830","display_name":"Nishant A. Mehta","orcid":"https://orcid.org/0000-0002-9639-0124"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nishant Mehta","raw_affiliation_strings":["Department of Computer Science, University of Victoria, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030352549"],"corresponding_institution_ids":["https://openalex.org/I212119943"],"apc_list":null,"apc_paid":null,"fwci":0.8144,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80510512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"258","last_page":"266"},"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":0.9994000196456909,"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":0.9940000176429749,"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/computer-science","display_name":"Computer science","score":0.8590866327285767},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7609341144561768},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.742077648639679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7024810314178467},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6560355424880981},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.585634708404541},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5347480177879333},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5048035383224487},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.45120465755462646},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4496215581893921},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43913891911506653},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42730221152305603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3724285364151001},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11447149515151978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8590866327285767},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7609341144561768},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.742077648639679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7024810314178467},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6560355424880981},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.585634708404541},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5347480177879333},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5048035383224487},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.45120465755462646},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4496215581893921},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43913891911506653},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42730221152305603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3724285364151001},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11447149515151978},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-5428","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5428","pdf_url":"https://www.aclweb.org/anthology/W18-5428.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 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-5428","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5428","pdf_url":"https://www.aclweb.org/anthology/W18-5428.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 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2911665948.pdf","grobid_xml":"https://content.openalex.org/works/W2911665948.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W151377110","https://openalex.org/W591184081","https://openalex.org/W1614298861","https://openalex.org/W1810943226","https://openalex.org/W1899794420","https://openalex.org/W1938755728","https://openalex.org/W1951216520","https://openalex.org/W2064675550","https://openalex.org/W2087946919","https://openalex.org/W2101234009","https://openalex.org/W2101609803","https://openalex.org/W2110485445","https://openalex.org/W2116261113","https://openalex.org/W2136848157","https://openalex.org/W2157331557","https://openalex.org/W2158139315","https://openalex.org/W2187089797","https://openalex.org/W2251012068","https://openalex.org/W2251253014","https://openalex.org/W2292919134","https://openalex.org/W2428136159","https://openalex.org/W2554915555","https://openalex.org/W2601243251","https://openalex.org/W2752194699","https://openalex.org/W2799149681","https://openalex.org/W2899771611","https://openalex.org/W2949563612","https://openalex.org/W2950577311","https://openalex.org/W2951559648","https://openalex.org/W2964159778","https://openalex.org/W4248358431","https://openalex.org/W4254816979"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W3045696640","https://openalex.org/W2160451571","https://openalex.org/W2495256954","https://openalex.org/W2944691285"],"abstract_inverted_index":{"While":[0],"Long":[1],"Short-Term":[2],"Memory":[3],"networks":[4],"(LSTMs)":[5],"and":[6,88],"other":[7],"forms":[8],"of":[9,28,41,72,94,117],"recurrent":[10],"neural":[11],"network":[12],"have":[13],"been":[14],"successfully":[15],"applied":[16],"to":[17,34,51,69,91,112],"language":[18],"modeling":[19],"on":[20,65],"a":[21,43,73,99],"character":[22],"level,":[23],"the":[24,38,47,55,59,70,83,106,114,118,135],"hidden":[25,39,60,107],"state":[26,61,108],"dynamics":[27],"these":[29],"models":[30],"can":[31],"be":[32],"difficult":[33],"interpret.":[35],"We":[36,96],"investigate":[37,113],"states":[40],"such":[42],"model":[44],"by":[45],"using":[46],"HDB-SCAN":[48],"clustering":[49],"algorithm":[50],"identify":[52,92],"points":[53],"in":[54,110,134],"text":[56],"at":[57],"which":[58],"is":[62],"similar.":[63],"Focusing":[64],"whitespace":[66],"characters":[67],"prior":[68],"beginning":[71],"word":[74,103,121],"reveals":[75],"interpretable":[76],"clusters":[77],"that":[78,130],"offer":[79],"insight":[80],"into":[81],"how":[82],"LSTM":[84],"may":[85],"combine":[86],"contextual":[87],"character-level":[89],"information":[90,126],"parts":[93],"speech.":[95],"also":[97],"introduce":[98],"method":[100],"for":[101,128],"deriving":[102],"vectors":[104,122],"from":[105],"representation":[109],"order":[111],"word-level":[115],"knowledge":[116],"model.":[119],"These":[120],"encode":[123],"meaningful":[124],"semantic":[125],"even":[127],"words":[129],"appear":[131],"only":[132],"once":[133],"training":[136],"text.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}