{"id":"https://openalex.org/W2887192000","doi":"https://doi.org/10.48550/arxiv.1808.04963","title":"Multiple Character Embeddings for Chinese Word Segmentation","display_name":"Multiple Character Embeddings for Chinese Word Segmentation","publication_year":2018,"publication_date":"2018-08-15","ids":{"openalex":"https://openalex.org/W2887192000","doi":"https://doi.org/10.48550/arxiv.1808.04963","mag":"2887192000"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1808.04963","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.04963","pdf_url":"https://arxiv.org/pdf/1808.04963","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1808.04963","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026746739","display_name":"Jingkang Wang","orcid":"https://orcid.org/0000-0001-9976-2432","observed_orcids":["https://orcid.org/0000-0001-9976-2432"]},"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":"Wang, Jingkang","raw_affiliation_strings":["The Lab of Information Content Intelligent Analysis , Shanghai , China School of Cyber Science and Engineering , Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Lab of Information Content Intelligent Analysis , Shanghai , China School of Cyber Science and Engineering , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101140082","display_name":"Jianing Zhou","orcid":"https://orcid.org/0009-0000-9897-2446","observed_orcids":["https://orcid.org/0009-0000-9897-2446","https://orcid.org/0009-0003-7191-6016"]},"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":"Zhou, Jianing","raw_affiliation_strings":["The Lab of Information Content Intelligent Analysis , Shanghai , China School of Cyber Science and Engineering , Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Lab of Information Content Intelligent Analysis , Shanghai , China School of Cyber Science and Engineering , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024102664","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0002-3371-6780","observed_orcids":["https://orcid.org/0000-0002-3371-6780"]},"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":"Zhou, Jie","raw_affiliation_strings":["The Lab of Information Content Intelligent Analysis , Shanghai , China School of Cyber Science and Engineering , Shanghai Jiao Tong University","Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Lab of Information Content Intelligent Analysis , Shanghai , China School of Cyber Science and Engineering , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085695760","display_name":"Gongshen Liu","orcid":"https://orcid.org/0000-0001-5194-1570","observed_orcids":["https://orcid.org/0000-0001-5194-1570"]},"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":"Liu, Gongshen","raw_affiliation_strings":["The Lab of Information Content Intelligent Analysis , Shanghai , China School of Cyber Science and Engineering , Shanghai Jiao Tong University","Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Lab of Information Content Intelligent Analysis , Shanghai , China School of Cyber Science and Engineering , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9307000041007996,"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":0.9307000041007996,"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":0.05649999901652336,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.002199999988079071,"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/chinese-word-segmentation","display_name":"Chinese word segmentation","score":1.0},{"id":"https://openalex.org/keywords/character-level-embeddings","display_name":"character embeddings","score":0.8989999890327454},{"id":"https://openalex.org/keywords/pinyin-romanization","display_name":"Pinyin romanization","score":0.8259999752044678},{"id":"https://openalex.org/keywords/feature-fusion","display_name":"feature fusion","score":0.6660000085830688},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"sequence labeling","score":0.5899999737739563}],"concepts":[{"id":"https://openalex.org/C2781095461","wikidata":"https://www.wikidata.org/wiki/Q42222","display_name":"Pinyin","level":3,"score":0.8251595497131348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199508190155029},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7283771634101868},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7106577157974243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6544473171234131},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5598263740539551},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5042620897293091},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.4943065643310547},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.46571779251098633},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4532318413257599},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.4383183717727661},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4369544982910156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34155377745628357},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26374104619026184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1808.04963","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.04963","pdf_url":"https://arxiv.org/pdf/1808.04963","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1808.04963","doi":"https://doi.org/10.48550/arxiv.1808.04963","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.04963","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1808.04963","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.04963","pdf_url":"https://arxiv.org/pdf/1808.04963","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1748265143","display_name":null,"funder_award_id":"U1736207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7471937628","display_name":"\u6587\u672c\u7eb9\u7406\u6a21\u578b\u53ca\u5176\u5728\u6d89\u6050\u60c5\u62a5\u5206\u6790\u9886\u57df\u7684\u5e94\u7528\u7814\u7a76","funder_award_id":"61772337","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W25062297","https://openalex.org/W1594229598","https://openalex.org/W1940872118","https://openalex.org/W2036516910","https://openalex.org/W2096204319","https://openalex.org/W2153579005","https://openalex.org/W2160513510","https://openalex.org/W2163377725","https://openalex.org/W2250623963","https://openalex.org/W2250739653","https://openalex.org/W2274880506","https://openalex.org/W2296283641","https://openalex.org/W2516334389","https://openalex.org/W2768669181","https://openalex.org/W2780528146","https://openalex.org/W2896649846","https://openalex.org/W2962902328","https://openalex.org/W2963355640","https://openalex.org/W2963628345","https://openalex.org/W2964093505","https://openalex.org/W2964352165"],"related_works":["https://openalex.org/W4385493412","https://openalex.org/W3159297355","https://openalex.org/W1575804004","https://openalex.org/W2386864954","https://openalex.org/W380382270","https://openalex.org/W3123716854","https://openalex.org/W1788792945","https://openalex.org/W2101906057","https://openalex.org/W2371267009","https://openalex.org/W2372811119"],"abstract_inverted_index":{"Chinese":[0,36],"word":[1],"segmentation":[2],"(CWS)":[3],"is":[4],"often":[5],"regarded":[6],"as":[7],"a":[8,73,103],"character-based":[9],"sequence":[10],"labeling":[11,107],"task":[12],"in":[13,66,106,115],"most":[14],"current":[15],"works":[16,31],"which":[17,60],"have":[18],"achieved":[19],"great":[20],"success":[21],"with":[22,120],"the":[23,85,89,112],"help":[24,101],"of":[25,59,69,123],"powerful":[26],"neural":[27],"networks.":[28],"However,":[29],"these":[30],"neglect":[32],"an":[33],"important":[34],"clue:":[35],"characters":[37],"incorporate":[38],"both":[39,58],"semantic":[40],"and":[41,55,64,117,125],"phonetic":[42],"meanings.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,110],"introduce":[48],"multiple":[49],"character":[50],"embeddings":[51,100],"including":[52],"Pinyin":[53],"Romanization":[54],"Wubi":[56],"Input,":[57],"are":[61],"easily":[62],"accessible":[63],"effective":[65],"depicting":[67],"semantics":[68],"characters.":[70],"We":[71],"propose":[72],"novel":[74],"shared":[75],"Bi-LSTM-CRF":[76],"model":[77],"to":[78],"fuse":[79],"linguistic":[80],"features":[81],"efficiently":[82],"by":[83],"sharing":[84],"LSTM":[86],"network":[87],"during":[88],"training":[90],"procedure.":[91],"Extensive":[92],"experiments":[93],"on":[94],"five":[95],"corpora":[96,119],"show":[97],"that":[98],"extra":[99],"obtain":[102],"significant":[104],"improvement":[105],"accuracy.":[108],"Specifically,":[109],"achieve":[111],"state-of-the-art":[113],"performance":[114],"AS":[116],"CityU":[118],"F1":[121],"scores":[122],"96.9":[124],"97.3,":[126],"respectively":[127],"without":[128],"leveraging":[129],"any":[130],"external":[131],"lexical":[132],"resources.":[133]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}