{"id":"https://openalex.org/W2833069259","doi":"https://doi.org/10.1177/0165551518786676","title":"Detecting new Chinese words from massive domain texts with word embedding","display_name":"Detecting new Chinese words from massive domain texts with word embedding","publication_year":2018,"publication_date":"2018-07-10","ids":{"openalex":"https://openalex.org/W2833069259","doi":"https://doi.org/10.1177/0165551518786676","mag":"2833069259"},"language":"en","primary_location":{"id":"doi:10.1177/0165551518786676","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551518786676","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","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/A5071508227","display_name":"Yu Qian","orcid":"https://orcid.org/0000-0003-0373-9815"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Qian","raw_affiliation_strings":["School of Management and Economics, University of Electronic Science and Technology of China, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Management and Economics, University of Electronic Science and Technology of China, P.R. China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101504057","display_name":"Yang Du","orcid":"https://orcid.org/0000-0002-4926-9233"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Du","raw_affiliation_strings":["School of Management and Economics, University of Electronic Science and Technology of China, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Management and Economics, University of Electronic Science and Technology of China, P.R. China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043781753","display_name":"Xiongwen Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongwen Deng","raw_affiliation_strings":["School of Management and Economics, University of Electronic Science and Technology of China, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Management and Economics, University of Electronic Science and Technology of China, P.R. China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003795905","display_name":"Baojun Ma","orcid":"https://orcid.org/0000-0002-2274-3089"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baojun Ma","raw_affiliation_strings":["Research Center for Big Data Management & Intelligent Decision, School of Economics and Management, Beijing University of Posts and Telecommunications, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Big Data Management & Intelligent Decision, School of Economics and Management, Beijing University of Posts and Telecommunications, P.R. China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048871520","display_name":"Qiongwei Ye","orcid":"https://orcid.org/0000-0002-6948-3894"},"institutions":[{"id":"https://openalex.org/I49185572","display_name":"Yunnan University of Finance And Economics","ror":"https://ror.org/04rhev598","country_code":"CN","type":"education","lineage":["https://openalex.org/I49185572"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiongwei Ye","raw_affiliation_strings":["School of Business, Yunnan University of Finance and Economics, P.R. China; School of Economics and Management, Tsinghua University, P.R. China","School of Economics and Management, Tsinghua University, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Business, Yunnan University of Finance and Economics, P.R. China; School of Economics and Management, Tsinghua University, P.R. China","institution_ids":["https://openalex.org/I49185572","https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Economics and Management, Tsinghua University, P.R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103819111","display_name":"Hua Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Yuan","raw_affiliation_strings":["School of Management and Economics, University of Electronic Science and Technology of China, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Management and Economics, University of Electronic Science and Technology of China, P.R. China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003795905"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":{"value":3650,"currency":"USD","value_usd":3650},"apc_paid":null,"fwci":1.0078,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.83443776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"45","issue":"2","first_page":"196","last_page":"211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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":0.9975000023841858,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9973000288009644,"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":0.9972000122070312,"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":0.8124574422836304},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7887477874755859},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6955302953720093},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.6598312854766846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6527407169342041},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5788318514823914},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.549968957901001},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.5472951531410217},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4966052174568176},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4828389286994934},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4320406913757324},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3355092406272888},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.19292274117469788},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18467718362808228},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.17783570289611816},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13893067836761475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8124574422836304},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7887477874755859},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6955302953720093},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.6598312854766846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6527407169342041},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5788318514823914},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.549968957901001},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.5472951531410217},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4966052174568176},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4828389286994934},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4320406913757324},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3355092406272888},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.19292274117469788},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18467718362808228},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.17783570289611816},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13893067836761475},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0165551518786676","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551518786676","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3265770646","display_name":"\u57fa\u4e8e\u79fb\u52a8\u5927\u6570\u636e\u7684\u7528\u6237\u884c\u4e3a\u6ea2\u51fa\u6548\u5e94\u7814\u7a76","funder_award_id":"71772017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3853465991","display_name":null,"funder_award_id":"17GLB009","funder_id":"https://openalex.org/F4320334112","funder_display_name":"Beijing Municipal Social Science Foundation"},{"id":"https://openalex.org/G3985448763","display_name":"\u9762\u5411\u79fb\u52a8\u5546\u52a1\u7684\u4e30\u5bcc\u6027\u4fe1\u606f\u8bc4\u4f30\u4e0e\u63d0\u53d6\u65b9\u6cd5\u7814\u7a76","funder_award_id":"71402007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4908734877","display_name":"\u5bcc\u4fe1\u606f\u73af\u5883\u4e0b\u57fa\u4e8e\u5174\u8da3\u6a21\u5f0f\u7684\u63a8\u8350\u7cfb\u7edf\u7814\u7a76","funder_award_id":"71271044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6507707097","display_name":"\u9762\u5411\u7528\u6237\u51b3\u7b56\u7684\u591a\u7c92\u5ea6\u4e3b\u9898\u4fe1\u606f\u7ed3\u6784\u62bd\u53d6\u53ca\u884c\u4e3a\u673a\u7406\u7814\u7a76","funder_award_id":"71671027","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7224177937","display_name":"\u7535\u5b50\u5546\u52a1\u73af\u5883\u4e0b\u57fa\u4e8e\u5927\u6570\u636e\u7684\u60c5\u666f\u5b9a\u4ef7\u4e0e\u4ea7\u54c1\u7ec4\u5408\u63a8\u5e7f\u673a\u5236\u7814\u7a76","funder_award_id":"71572029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8892984891","display_name":null,"funder_award_id":"71490723","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/F4320334112","display_name":"Beijing Municipal Social Science Foundation","ror":"https://ror.org/01xp57w77"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W136741500","https://openalex.org/W392761142","https://openalex.org/W1810889649","https://openalex.org/W1969183489","https://openalex.org/W1972245381","https://openalex.org/W1979285701","https://openalex.org/W1986216695","https://openalex.org/W1991098482","https://openalex.org/W1997455322","https://openalex.org/W2114210953","https://openalex.org/W2137012502","https://openalex.org/W2140016149","https://openalex.org/W2140190241","https://openalex.org/W2141520705","https://openalex.org/W2179637284","https://openalex.org/W2210309660","https://openalex.org/W2263662513","https://openalex.org/W2328317444","https://openalex.org/W2406555490","https://openalex.org/W2408754830","https://openalex.org/W2483327705","https://openalex.org/W2507159018","https://openalex.org/W2593581739","https://openalex.org/W2612817216","https://openalex.org/W2912145841","https://openalex.org/W4231080135","https://openalex.org/W4236095894","https://openalex.org/W4237177941","https://openalex.org/W4285719527","https://openalex.org/W4299626704","https://openalex.org/W4401042337"],"related_works":["https://openalex.org/W2964015157","https://openalex.org/W4301653298","https://openalex.org/W2119262534","https://openalex.org/W152351265","https://openalex.org/W1970026646","https://openalex.org/W3042295250","https://openalex.org/W2994651536","https://openalex.org/W4232755842","https://openalex.org/W2765918440","https://openalex.org/W4237027867"],"abstract_inverted_index":{"Textual":[0],"information":[1,67],"retrieval":[2],"(TIR)":[3],"is":[4],"based":[5,141,164],"on":[6,142,165],"the":[7,19,63,78,143,148,160,166,172],"relationship":[8],"between":[9,68],"word":[10,13,20,53,59,87,105,114,123,144,152,169],"units.":[11],"Traditional":[12],"segmentation":[14],"techniques":[15],"attempt":[16],"to":[17,29,61,111,127,146],"discern":[18],"units":[21,106,170],"accurately":[22],"from":[23,98,193],"texts;":[24],"however,":[25],"they":[26],"are":[27],"unable":[28],"appropriately":[30],"and":[31,65,89],"efficiently":[32],"identify":[33,128],"all":[34,104],"new":[35,39,96,134,156,191],"words.":[36,135],"Identification":[37],"of":[38,131,150,162,168],"words,":[40],"especially":[41],"in":[42,70,107,171,189],"languages":[43],"such":[44],"as":[45],"Chinese,":[46],"remains":[47],"a":[48,71,82,108,112,120,129,138,151,155,176,186],"challenge.":[49],"In":[50,73,175],"recent":[51],"years,":[52],"embedding":[54,88],"methods":[55],"have":[56],"used":[57,119],"numerical":[58],"vectors":[60,145],"retain":[62],"semantic":[64],"correlated":[66],"words":[69,97,192],"corpus.":[72],"this":[74],"article,":[75],"we":[76,102,118],"propose":[77],"word-embedding-based":[79],"method":[80,84,126],"(WEBM),":[81],"novel":[83],"that":[85,183],"combines":[86],"frequent":[90,121],"n-gram":[91,122],"string":[92,124,153],"mining":[93,125],"for":[94,133],"discovering":[95],"domain":[99,109],"corpora.":[100,196],"First,":[101],"mapped":[103],"corpus":[110],"high-dimension":[113],"vector":[115],"space.":[116],"Second,":[117],"set":[130],"candidates":[132,163],"We":[136],"designed":[137],"pruning":[139],"strategy":[140],"quantify":[147],"possibility":[149],"being":[154],"word,":[157],"thereby":[158],"allowing":[159],"evaluation":[161],"similarity":[167],"same":[173],"string.":[174],"comparative":[177],"study,":[178],"our":[179],"experimental":[180],"results":[181],"revealed":[182],"WEBM":[184],"had":[185],"great":[187],"advantage":[188],"detecting":[190],"massive":[194],"Chinese":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-10-10T00:00:00"}