{"id":"https://openalex.org/W2952487930","doi":"https://doi.org/10.18653/v1/p19-1143","title":"Training Hybrid Language Models by Marginalizing over Segmentations","display_name":"Training Hybrid Language Models by Marginalizing over Segmentations","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2952487930","doi":"https://doi.org/10.18653/v1/p19-1143","mag":"2952487930"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1143","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1143","pdf_url":"https://www.aclweb.org/anthology/P19-1143.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1143.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069316249","display_name":"\u00c9douard Grave","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Edouard Grave","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060255128","display_name":"Sainbayar Sukhbaatar","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sainbayar Sukhbaatar","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035420035","display_name":"Piotr Bojanowski","orcid":"https://orcid.org/0000-0001-8098-5900"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Piotr Bojanowski","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107859338","display_name":"Armand Joulin","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Armand Joulin","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3015,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.85487959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1477","last_page":"1482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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/string","display_name":"String (physics)","score":0.7984881401062012},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7750204801559448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.745013952255249},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6020551919937134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5907579660415649},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5722650289535522},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.527050256729126},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17689338326454163}],"concepts":[{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7984881401062012},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7750204801559448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745013952255249},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6020551919937134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5907579660415649},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5722650289535522},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.527050256729126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17689338326454163},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1143","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1143","pdf_url":"https://www.aclweb.org/anthology/P19-1143.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1143","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1143","pdf_url":"https://www.aclweb.org/anthology/P19-1143.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952487930.pdf","grobid_xml":"https://content.openalex.org/works/W2952487930.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1966812932","https://openalex.org/W2146502635","https://openalex.org/W2510842514","https://openalex.org/W2525246036","https://openalex.org/W2592647456","https://openalex.org/W2609370997","https://openalex.org/W2727642071","https://openalex.org/W2906625520","https://openalex.org/W2962784628","https://openalex.org/W2963077280","https://openalex.org/W2963088785","https://openalex.org/W2963304263","https://openalex.org/W2963357986","https://openalex.org/W2963403868","https://openalex.org/W2963494889","https://openalex.org/W2963735467","https://openalex.org/W2963831883","https://openalex.org/W2963899393","https://openalex.org/W2963983719","https://openalex.org/W2964019776","https://openalex.org/W2964325845","https://openalex.org/W2998704965","https://openalex.org/W4285719527","https://openalex.org/W4294555862","https://openalex.org/W4298422451","https://openalex.org/W4299548129","https://openalex.org/W4302375066","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4251972423","https://openalex.org/W1503216044","https://openalex.org/W2393609567","https://openalex.org/W2369369044","https://openalex.org/W2354143083","https://openalex.org/W2372906645","https://openalex.org/W4319998713","https://openalex.org/W2366269494","https://openalex.org/W2353650902","https://openalex.org/W2347884623"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,69],"study":[4],"the":[5,52,58,61,65,78,85],"problem":[6],"of":[7,54,60,63,88],"hybrid":[8],"language":[9,108],"modeling,":[10],"that":[11],"is":[12,57,73],"using":[13,44,48],"models":[14],"which":[15],"can":[16],"predict":[17],"both":[18],"characters":[19,49],"and":[20,46],"larger":[21],"units":[22],"such":[23,30],"as":[24],"character":[25,106],"ngrams":[26],"or":[27],"words.":[28],"Using":[29],"models,":[31],"multiple":[32],"potential":[33],"segmentations":[34,79],"usually":[35],"exist":[36],"for":[37,41],"a":[38,55,89,104],"given":[39],"string,":[40],"example":[42],"one":[43,47],"words":[45],"only.":[50],"Thus,":[51],"probability":[53,87],"string":[56],"sum":[59],"probabilities":[62],"all":[64],"possible":[66,74],"segmentations.":[67],"Here,":[68],"show":[70],"how":[71],"it":[72],"to":[75,83],"marginalize":[76],"over":[77,103],"efficiently,":[80],"in":[81],"order":[82],"compute":[84],"true":[86],"sequence.":[90],"We":[91],"apply":[92],"our":[93],"technique":[94],"on":[95],"three":[96],"datasets,":[97],"comprising":[98],"seven":[99],"languages,":[100],"showing":[101],"improvements":[102],"strong":[105],"level":[107],"model.":[109]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}