{"id":"https://openalex.org/W2964047576","doi":"https://doi.org/10.1109/taslp.2019.2922537","title":"Effective Subword Segmentation for Text Comprehension","display_name":"Effective Subword Segmentation for Text Comprehension","publication_year":2019,"publication_date":"2019-06-12","ids":{"openalex":"https://openalex.org/W2964047576","doi":"https://doi.org/10.1109/taslp.2019.2922537","mag":"2964047576"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2922537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2922537","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","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/A5070962435","display_name":"Zhuosheng Zhang","orcid":"https://orcid.org/0000-0002-4183-3645"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuosheng Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4183-3645","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036050911","display_name":"Hai Zhao","orcid":"https://orcid.org/0000-0001-7290-0487"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7290-0487","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016005679","display_name":"Kangwei Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangwei Ling","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047636121","display_name":"Jiangtong Li","orcid":"https://orcid.org/0000-0003-3873-4053"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangtong Li","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3873-4053","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002584135","display_name":"Zuchao Li","orcid":"https://orcid.org/0000-0003-0436-8446"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuchao Li","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0436-8446","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067842807","display_name":"Shexia He","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shexia He","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101990229","display_name":"Guohong Fu","orcid":"https://orcid.org/0000-0001-6882-6181"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohong Fu","raw_affiliation_strings":["Institute of Artificial Intelligence, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0945,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.95124583,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"27","issue":"11","first_page":"1664","last_page":"1674"},"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":0.9998999834060669,"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/T13629","display_name":"Text Readability and Simplification","score":0.995199978351593,"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/natural-language-processing","display_name":"Natural language processing","score":0.7458406686782837},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7390845417976379},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6767845153808594},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6543455123901367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6509861350059509},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5952965617179871},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.575835645198822},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5429782867431641},{"id":"https://openalex.org/keywords/reading-comprehension","display_name":"Reading comprehension","score":0.526171088218689},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5118202567100525},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4873872399330139},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4215743839740753},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.42064863443374634},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4116094410419464},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3155021667480469},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10466966032981873}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7458406686782837},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390845417976379},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6767845153808594},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6543455123901367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6509861350059509},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5952965617179871},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.575835645198822},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5429782867431641},{"id":"https://openalex.org/C2778780117","wikidata":"https://www.wikidata.org/wiki/Q3269423","display_name":"Reading comprehension","level":3,"score":0.526171088218689},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5118202567100525},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4873872399330139},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4215743839740753},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.42064863443374634},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4116094410419464},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3155021667480469},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10466966032981873},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2922537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2922537","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8799999952316284}],"awards":[{"id":"https://openalex.org/G4276612039","display_name":null,"funder_award_id":"2017YFB0304100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W1026270304","https://openalex.org/W1505680913","https://openalex.org/W1522301498","https://openalex.org/W1528203680","https://openalex.org/W1544827683","https://openalex.org/W1614298861","https://openalex.org/W1840435438","https://openalex.org/W1938755728","https://openalex.org/W1995875735","https://openalex.org/W2126209950","https://openalex.org/W2154756108","https://openalex.org/W2169147927","https://openalex.org/W2404744763","https://openalex.org/W2417763662","https://openalex.org/W2493916176","https://openalex.org/W2516196286","https://openalex.org/W2551396370","https://openalex.org/W2558203065","https://openalex.org/W2593833795","https://openalex.org/W2606342375","https://openalex.org/W2608787653","https://openalex.org/W2739845275","https://openalex.org/W2740743644","https://openalex.org/W2740747242","https://openalex.org/W2760082451","https://openalex.org/W2787933937","https://openalex.org/W2798524681","https://openalex.org/W2803739890","https://openalex.org/W2810134635","https://openalex.org/W2810519866","https://openalex.org/W2822830299","https://openalex.org/W2859207840","https://openalex.org/W2889181558","https://openalex.org/W2890176538","https://openalex.org/W2892085193","https://openalex.org/W2911529999","https://openalex.org/W2949446780","https://openalex.org/W2949615363","https://openalex.org/W2950175955","https://openalex.org/W2950577311","https://openalex.org/W2950621961","https://openalex.org/W2951534261","https://openalex.org/W2951559648","https://openalex.org/W2951709801","https://openalex.org/W2962718483","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2962809918","https://openalex.org/W2962934410","https://openalex.org/W2963022746","https://openalex.org/W2963324947","https://openalex.org/W2963339397","https://openalex.org/W2963344337","https://openalex.org/W2963582782","https://openalex.org/W2963595025","https://openalex.org/W2963626623","https://openalex.org/W2963748441","https://openalex.org/W2963756346","https://openalex.org/W2963898730","https://openalex.org/W2963956494","https://openalex.org/W2964082993","https://openalex.org/W2964121744","https://openalex.org/W2964185324","https://openalex.org/W2964267515","https://openalex.org/W2964302308","https://openalex.org/W2964352165","https://openalex.org/W2998579922","https://openalex.org/W3099023595","https://openalex.org/W3104486441","https://openalex.org/W4289377895","https://openalex.org/W4302343710","https://openalex.org/W6601894380","https://openalex.org/W6626481562","https://openalex.org/W6630160514","https://openalex.org/W6631190155","https://openalex.org/W6632455782","https://openalex.org/W6636510571","https://openalex.org/W6640598943","https://openalex.org/W6678478121","https://openalex.org/W6713412409","https://openalex.org/W6725698578","https://openalex.org/W6729322275","https://openalex.org/W6729654139","https://openalex.org/W6729938257","https://openalex.org/W6742080785","https://openalex.org/W6744505285","https://openalex.org/W6748204104","https://openalex.org/W6751679225","https://openalex.org/W6752682135","https://openalex.org/W6752695545","https://openalex.org/W6752820230","https://openalex.org/W6752918764","https://openalex.org/W6754235287","https://openalex.org/W6757183776","https://openalex.org/W6758528834","https://openalex.org/W6763291536"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2951819827","https://openalex.org/W2849310602","https://openalex.org/W2082296339","https://openalex.org/W2030403248","https://openalex.org/W2161828220","https://openalex.org/W1972348076"],"abstract_inverted_index":{"Representation":[0],"learning":[1,67],"is":[2,34],"the":[3,22,50],"foundation":[4],"of":[5,24,53,78,103],"machine":[6],"reading":[7],"comprehension":[8],"and":[9,68,85,110],"inference.":[10],"In":[11],"state-of-the-art":[12],"models,":[13],"character-level":[14],"representations":[15],"have":[16],"been":[17],"broadly":[18],"adopted":[19],"to":[20,48],"alleviate":[21],"problem":[23],"effectively":[25],"representing":[26],"rare":[27],"or":[28,43],"complex":[29],"words.":[30],"However,":[31],"character":[32],"itself":[33],"not":[35],"a":[36,61,76],"natural":[37],"minimal":[38],"linguistic":[39,51],"unit":[40],"for":[41,66,82,89],"representation":[42],"word":[44],"embedding":[45,64,95],"composing":[46,69],"due":[47],"ignoring":[49],"coherence":[52],"consecutive":[54],"characters":[55],"inside":[56],"word.":[57],"This":[58],"paper":[59],"presents":[60],"general":[62],"subword-augmented":[63,87,94],"framework":[65],"computationally":[70],"derived":[71],"subword-level":[72],"representations.":[73],"We":[74],"survey":[75],"series":[77],"unsupervised":[79],"segmentation":[80],"methods":[81],"subword":[83],"acquisition":[84],"different":[86],"strategies":[88],"text":[90,104],"understanding,":[91],"showing":[92],"that":[93],"significantly":[96],"improves":[97],"our":[98],"baselines":[99],"in":[100],"various":[101],"types":[102],"understanding":[105],"tasks":[106],"on":[107],"both":[108],"English":[109],"Chinese":[111],"benchmarks.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}