{"id":"https://openalex.org/W2891680269","doi":"https://doi.org/10.18653/v1/d18-1059","title":"Generalizing Word Embeddings using Bag of Subwords","display_name":"Generalizing Word Embeddings using Bag of Subwords","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2891680269","doi":"https://doi.org/10.18653/v1/d18-1059","mag":"2891680269"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1059","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1059","pdf_url":"https://www.aclweb.org/anthology/D18-1059.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/D18-1059.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036110657","display_name":"Jinman Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jinman Zhao","raw_affiliation_strings":["Department of Computer Sciences University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113876331","display_name":"Sidharth Mudgal","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sidharth Mudgal","raw_affiliation_strings":["Department of Computer Sciences University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035905957","display_name":"Yingyu Liang","orcid":"https://orcid.org/0000-0002-3644-774X"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingyu Liang","raw_affiliation_strings":["Department of Computer Sciences University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036110657"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":6.581,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.97311569,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"601","last_page":"606"},"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":0.9941999912261963,"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/word","display_name":"Word (group theory)","score":0.8149759769439697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7635282278060913},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7256558537483215},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6932170391082764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6657871007919312},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6604111194610596},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6171203851699829},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.45110711455345154},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36989814043045044},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19656458497047424},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14887860417366028}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.8149759769439697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635282278060913},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7256558537483215},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6932170391082764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6657871007919312},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6604111194610596},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6171203851699829},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.45110711455345154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36989814043045044},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19656458497047424},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14887860417366028},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/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/d18-1059","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1059","pdf_url":"https://www.aclweb.org/anthology/D18-1059.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/d18-1059","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1059","pdf_url":"https://www.aclweb.org/anthology/D18-1059.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306555","display_name":"Wisconsin Alumni Research Foundation","ror":"https://ror.org/00hwxbz16"},{"id":"https://openalex.org/F4320309434","display_name":"University of Wisconsin-Madison","ror":"https://ror.org/01y2jtd41"},{"id":"https://openalex.org/F4320337368","display_name":"Division of Graduate Education","ror":"https://ror.org/00whkrf32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2891680269.pdf","grobid_xml":"https://content.openalex.org/works/W2891680269.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1505680913","https://openalex.org/W1523296404","https://openalex.org/W1899794420","https://openalex.org/W2040711288","https://openalex.org/W2053921957","https://openalex.org/W2067438047","https://openalex.org/W2101609803","https://openalex.org/W2142377809","https://openalex.org/W2143995218","https://openalex.org/W2153579005","https://openalex.org/W2250539671","https://openalex.org/W2251012068","https://openalex.org/W2294970769","https://openalex.org/W2295097532","https://openalex.org/W2463895987","https://openalex.org/W2493916176","https://openalex.org/W2963042536","https://openalex.org/W2963216505","https://openalex.org/W2963421945","https://openalex.org/W2963626623","https://openalex.org/W2964005834","https://openalex.org/W2964090065","https://openalex.org/W4294170691"],"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/W1585007175","https://openalex.org/W2366269494","https://openalex.org/W2353650902"],"abstract_inverted_index":{"We":[0,17],"approach":[1],"the":[2,81],"problem":[3],"of":[4,30,66],"generalizing":[5],"pretrained":[6],"word":[7,21,59],"embeddings":[8],"beyond":[9],"fixed-size":[10],"vocabularies":[11],"without":[12],"using":[13],"additional":[14],"contextual":[15],"information.":[16],"propose":[18],"a":[19],"subwordlevel":[20],"vector":[22],"generation":[23],"model":[24,34,53],"that":[25,51],"views":[26],"words":[27],"as":[28],"bags":[29],"character":[31],"n-grams.":[32],"The":[33],"is":[35],"simple,":[36],"fast":[37],"to":[38],"train":[39],"and":[40,62,69,87],"provides":[41],"good":[42],"vectors":[43],"for":[44],"rare":[45],"or":[46],"unseen":[47],"words.":[48],"Experiments":[49],"show":[50],"our":[52,76],"achieves":[54],"stateof-the-art":[55],"performances":[56],"in":[57,63,72,79],"English":[58],"similarity":[60],"task":[61],"joint":[64],"prediction":[65],"part-ofspeech":[67],"tag":[68],"morphosyntactic":[70],"attributes":[71],"23":[73],"languages,":[74],"suggesting":[75],"model's":[77],"ability":[78],"capturing":[80],"relationship":[82],"between":[83],"words'":[84],"textual":[85],"representations":[86],"their":[88],"embeddings.":[89]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}