{"id":"https://openalex.org/W3098953385","doi":"https://doi.org/10.1109/crc51253.2020.9253493","title":"New Word Discovery Algorithm Based on N-Gram for Multi-word Internal Solidification Degree and Frequency","display_name":"New Word Discovery Algorithm Based on N-Gram for Multi-word Internal Solidification Degree and Frequency","publication_year":2020,"publication_date":"2020-10-16","ids":{"openalex":"https://openalex.org/W3098953385","doi":"https://doi.org/10.1109/crc51253.2020.9253493","mag":"3098953385"},"language":"en","primary_location":{"id":"doi:10.1109/crc51253.2020.9253493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/crc51253.2020.9253493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 5th International Conference on Control, Robotics and Cybernetics (CRC)","raw_type":"proceedings-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/A5100354509","display_name":"Xudong Li","orcid":"https://orcid.org/0000-0002-7891-4887"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xudong Li","raw_affiliation_strings":["School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053412068","display_name":"Xiangyang Chen","orcid":"https://orcid.org/0000-0002-6981-7022"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China","institution_ids":["https://openalex.org/I91125648"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100354509"],"corresponding_institution_ids":["https://openalex.org/I91125648"],"apc_list":null,"apc_paid":null,"fwci":1.3345,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86500113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9904999732971191,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9902999997138977,"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":0.7438990473747253},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.7228180766105652},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6363892555236816},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.6312385201454163},{"id":"https://openalex.org/keywords/degree","display_name":"Degree (music)","score":0.6092687845230103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5492687821388245},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5166902542114258},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5002326965332031},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4896271824836731},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.470040500164032},{"id":"https://openalex.org/keywords/word-lists-by-frequency","display_name":"Word lists by frequency","score":0.4686505198478699},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.467214971780777},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.45418065786361694},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44983065128326416},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43095076084136963},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37276652455329895},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3204330503940582},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.20269030332565308},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.1963241994380951},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18218639492988586},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.13387158513069153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7438990473747253},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.7228180766105652},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6363892555236816},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.6312385201454163},{"id":"https://openalex.org/C2775997480","wikidata":"https://www.wikidata.org/wiki/Q586277","display_name":"Degree (music)","level":2,"score":0.6092687845230103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5492687821388245},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5166902542114258},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5002326965332031},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4896271824836731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.470040500164032},{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.4686505198478699},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.467214971780777},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.45418065786361694},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44983065128326416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43095076084136963},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37276652455329895},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3204330503940582},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.20269030332565308},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.1963241994380951},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18218639492988586},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.13387158513069153},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/crc51253.2020.9253493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/crc51253.2020.9253493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 5th International Conference on Control, Robotics and Cybernetics (CRC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320325438","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1979285701","https://openalex.org/W2114982270","https://openalex.org/W2371202213","https://openalex.org/W2593720592","https://openalex.org/W2803439868","https://openalex.org/W2911855264","https://openalex.org/W2939021222"],"related_works":["https://openalex.org/W3136209078","https://openalex.org/W2566553554","https://openalex.org/W2032511029","https://openalex.org/W2147102537","https://openalex.org/W4238770060","https://openalex.org/W2360516640","https://openalex.org/W2110885608","https://openalex.org/W2233156216","https://openalex.org/W2251364186","https://openalex.org/W2381705608"],"abstract_inverted_index":{"For":[0],"the":[1,4,8,18,27,60,72,96,99,103,116,122,128,135,145,152,156,170],"problems":[2],"of":[3,7,29,45,56,64,112,172],"low":[5],"usability":[6],"lexicon":[9],"constructed":[10],"by":[11,106],"traditional":[12],"new":[13,20,34,157,164,173,182],"word":[14,21,35,107,158,165,174,183],"discovery":[15,36,166,184],"methods":[16],"and":[17,43,69,94,109,126,139],"erroneous":[19],"segmentation":[22,92],"results":[23],"that":[24,147,162],"only":[25,71],"consider":[26],"solidification":[28,42],"adjacent":[30],"two":[31],"characters,":[32],"A":[33],"algorithm":[37,167],"based":[38],"on":[39],"N-Gram's":[40],"internal":[41,61],"frequency":[44,108],"multiple":[46,132],"characters":[47],"is":[48,177],"proposed.":[49],"Firstly,":[50],"select":[51],"a":[52,76,81],"fixed":[53],"higher":[54,74],"degree":[55,63],"coagulation":[57,62],"n,":[58],"calculate":[59],"n":[65],"under":[66],"different":[67],"values,":[68],"keep":[70],"fragments":[73],"than":[75,180],"certain":[77],"threshold":[78],"to":[79,89,120,154],"form":[80],"set":[82],"Q.":[83],"Then":[84],"combine":[85],"named":[86],"entity":[87],"recognition":[88],"construct":[90],"N-Gram":[91],"corpus,":[93],"count":[95],"frequency.":[97],"Introduce":[98],"backtracking":[100],"mechanism,":[101],"filter":[102,127],"candidate":[104],"words":[105,130,146],"K":[110],"times":[111],"mutual":[113],"information,":[114],"use":[115],"Trie":[117],"tree":[118],"structure":[119],"improve":[121],"string":[123],"retrieval":[124],"speed,":[125],"meaningless":[129],"in":[131,151],"dimensions":[133],"through":[134],"rule":[136],"stop":[137,141],"vocabulary":[138],"Chinese":[140],"vocabulary.":[142],"Finally,":[143],"compare":[144],"do":[148],"not":[149],"appear":[150],"dictionary":[153],"get":[155],"set.":[159],"Experiments":[160],"show":[161],"this":[163],"effectively":[168],"improves":[169],"accuracy":[171],"recognition,":[175],"which":[176],"significantly":[178],"faster":[179],"other":[181],"algorithms.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}