{"id":"https://openalex.org/W2913726998","doi":"https://doi.org/10.1017/s1351324918000463","title":"Out-domain Chinese new word detection with statistics-based character embedding","display_name":"Out-domain Chinese new word detection with statistics-based character embedding","publication_year":2019,"publication_date":"2019-02-10","ids":{"openalex":"https://openalex.org/W2913726998","doi":"https://doi.org/10.1017/s1351324918000463","mag":"2913726998"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324918000463","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324918000463","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","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/A5013217360","display_name":"Yuzhi Liang","orcid":"https://orcid.org/0000-0001-6868-1971"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhi Liang","raw_affiliation_strings":["Department of Information Engineering, Peking University Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083369457","display_name":"Min Yang","orcid":"https://orcid.org/0000-0001-7345-5071"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Yang","raw_affiliation_strings":["Frontier Science and Technology Research Centre, Shenzhen Institutes of Advanced Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Frontier Science and Technology Research Centre, Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031653957","display_name":"Jia Zhu","orcid":"https://orcid.org/0000-0002-5959-390X"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jia Zhu","raw_affiliation_strings":["Department of Computer Science, South China Normal University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025130883","display_name":"Siu Ming Yiu","orcid":"https://orcid.org/0000-0002-3975-8500"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"S. M. Yiu","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031653957"],"corresponding_institution_ids":["https://openalex.org/I187400657"],"apc_list":null,"apc_paid":null,"fwci":1.2601,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84634285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"25","issue":"2","first_page":"239","last_page":"255"},"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":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9957000017166138,"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":0.8740490674972534},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7116941809654236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6519984006881714},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6463163495063782},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6103219389915466},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5799260139465332},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5751388072967529},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5342943072319031},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5274099111557007},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4851697087287903},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4259300231933594},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3015022277832031},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11168321967124939},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08326104283332825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8740490674972534},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7116941809654236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6519984006881714},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6463163495063782},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6103219389915466},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5799260139465332},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5751388072967529},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5342943072319031},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5274099111557007},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4851697087287903},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4259300231933594},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3015022277832031},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11168321967124939},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08326104283332825},{"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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324918000463","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324918000463","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W25062297","https://openalex.org/W1516184288","https://openalex.org/W1528012351","https://openalex.org/W1528203680","https://openalex.org/W1594229598","https://openalex.org/W1886814818","https://openalex.org/W1934019294","https://openalex.org/W1982498087","https://openalex.org/W2024094747","https://openalex.org/W2033295622","https://openalex.org/W2036516910","https://openalex.org/W2052816566","https://openalex.org/W2069634628","https://openalex.org/W2107078199","https://openalex.org/W2120661206","https://openalex.org/W2131988669","https://openalex.org/W2137281231","https://openalex.org/W2147880316","https://openalex.org/W2152104712","https://openalex.org/W2153579005","https://openalex.org/W2163377725","https://openalex.org/W2250626347","https://openalex.org/W2250739653","https://openalex.org/W2251811146","https://openalex.org/W2252225757","https://openalex.org/W2274880506","https://openalex.org/W2349699447","https://openalex.org/W2436788615","https://openalex.org/W2502289490","https://openalex.org/W2512395292","https://openalex.org/W2516334389","https://openalex.org/W2559372221","https://openalex.org/W2597601064","https://openalex.org/W2795330894","https://openalex.org/W2950577311","https://openalex.org/W2964352165","https://openalex.org/W3145501851","https://openalex.org/W3147254695","https://openalex.org/W4230872509","https://openalex.org/W4294170691","https://openalex.org/W4303105513","https://openalex.org/W6668157977","https://openalex.org/W6682691769","https://openalex.org/W6683955732"],"related_works":["https://openalex.org/W4288407670","https://openalex.org/W947140380","https://openalex.org/W2559372221","https://openalex.org/W2911655849","https://openalex.org/W4286432911","https://openalex.org/W4230884544","https://openalex.org/W4245453790","https://openalex.org/W3194985222","https://openalex.org/W3216571906","https://openalex.org/W3089171094"],"abstract_inverted_index":{"Abstract":[0],"Unlike":[1],"English":[2],"and":[3,13,23,72,98,204],"other":[4],"Western":[5],"languages,":[6],"many":[7],"Asian":[8],"languages":[9],"such":[10,92],"as":[11,41,93,196,212],"Chinese":[12,35,81,145,163,177,186,192],"Japanese":[14],"do":[15],"not":[16,132],"delimit":[17],"words":[18],"by":[19,50],"space.":[20],"Word":[21],"segmentation":[22,37,83,113],"new":[24,141,164,171,187],"word":[25,36,66,70,82,142,165,178,188],"detection":[26,143],"are":[27,131,210],"therefore":[28],"key":[29],"steps":[30],"in":[31,64,125,144,200,215],"processing":[32],"these":[33],"languages.":[34],"can":[38,47],"be":[39,86],"considered":[40],"a":[42,52,65,170,184,197],"part-of-speech":[43],"(POS)-tagging":[44],"problem.":[45],"We":[46,167],"segment":[48],"corpus":[49,153],"assigning":[51],"label":[53],"for":[54,69,74,147,176],"each":[55,191],"character":[56,63,193,209],"which":[57,126,148],"indicates":[58],"the":[59,62,75,78,112,119,140,149,201,208,213,216],"position":[60],"of":[61,77,136,151,207],"(e.g.,":[67],"\u201cB\u201d":[68],"beginning,":[71],"\u201cE\u201d":[73],"end":[76],"word,":[79],"etc.).":[80],"seems":[84],"to":[85,122],"well":[87],"studied.":[88],"Machine":[89],"learning":[90],"models":[91],"conditional":[94],"random":[95],"field":[96],"(CRF)":[97],"bi-directional":[99],"long":[100],"short-term":[101],"memory":[102],"(LSTM)":[103],"have":[104],"shown":[105],"outstanding":[106],"performances":[107],"on":[108,161],"this":[109,157],"task.":[110],"However,":[111],"accuracies":[114],"drop":[115],"significantly":[116],"when":[117],"applying":[118],"same":[120],"approaches":[121],"out-domain":[123,137,162],"cases,":[124],"high-quality":[127,152],"in-domain":[128],"training":[129],"data":[130],"available.":[133],"An":[134],"example":[135],"applications":[138],"is":[139,154,194],"microblogs":[146],"availability":[150],"limited.":[155],"In":[156],"paper,":[158],"we":[159,182],"focus":[160],"detection.":[166,180],"first":[168],"design":[169],"method":[172],"Edge":[173],"Likelihood":[174],"(EL)":[175],"boundary":[179],"Then":[181],"propose":[183],"domain-independent":[185],"detector":[189],"(DICND);":[190],"represented":[195],"low-dimensional":[198],"vector":[199],"proposed":[202],"framework,":[203],"segmentation-related":[205],"features":[206],"used":[211],"values":[214],"vector.":[217]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}