{"id":"https://openalex.org/W4372260351","doi":"https://doi.org/10.1109/icassp49357.2023.10097080","title":"Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Distant Supervision","display_name":"Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Distant Supervision","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260351","doi":"https://doi.org/10.1109/icassp49357.2023.10097080"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102020220","display_name":"Shuo Feng","orcid":"https://orcid.org/0000-0003-0058-3835"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuo Feng","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,China","Nanjing University of Aeronautics and Astronautics, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061435467","display_name":"Piji Li","orcid":"https://orcid.org/0000-0003-1474-3692"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Piji Li","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,China","Nanjing University of Aeronautics and Astronautics, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102020220"],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52330218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.9887999892234802,"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/computer-science","display_name":"Computer science","score":0.8068016767501831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6335475444793701},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6045942902565002},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6027420163154602},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.5788708925247192},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5660122036933899},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.5548421740531921},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4817957282066345},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4623391032218933},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4596227705478668},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.426790714263916},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39256444573402405},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1258387565612793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8068016767501831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6335475444793701},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6045942902565002},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6027420163154602},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.5788708925247192},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5660122036933899},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.5548421740531921},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4817957282066345},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4623391032218933},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4596227705478668},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.426790714263916},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39256444573402405},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1258387565612793},{"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322438","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W331019419","https://openalex.org/W2006969979","https://openalex.org/W2079442239","https://openalex.org/W2098830640","https://openalex.org/W2107598941","https://openalex.org/W2116343275","https://openalex.org/W2142384583","https://openalex.org/W2142523187","https://openalex.org/W2147880316","https://openalex.org/W2161044106","https://openalex.org/W2354581626","https://openalex.org/W2389539985","https://openalex.org/W2963096987","https://openalex.org/W2963907318","https://openalex.org/W2978400918","https://openalex.org/W3104182623","https://openalex.org/W3212108714","https://openalex.org/W6611342419","https://openalex.org/W6677674009","https://openalex.org/W6740005241","https://openalex.org/W6796912519"],"related_works":["https://openalex.org/W2393940967","https://openalex.org/W2385598138","https://openalex.org/W2346578824","https://openalex.org/W2366925922","https://openalex.org/W2159591557","https://openalex.org/W2115592387","https://openalex.org/W2905950556","https://openalex.org/W2112534334","https://openalex.org/W120168696","https://openalex.org/W2153245103"],"abstract_inverted_index":{"Ancient":[0],"Chinese":[1,20,40,60,109],"word":[2],"segmentation":[3],"(WSG)":[4],"and":[5,22,42,57,81,95,99,135],"part-of-speech":[6],"tagging":[7,24,44],"(POS)":[8],"are":[9,54],"important":[10],"to":[11,88,105],"study":[12],"ancient":[13,19,39,59,108],"Chinese,":[14],"but":[15],"the":[16,74,107,117,121,125,129,136],"amount":[17,84],"of":[18,38,73,77,85],"WSG":[21,41],"POS":[23,43],"data":[25,45,87,123,130],"is":[26,141],"still":[27,55],"rare.":[28],"In":[29],"this":[30,68,103],"paper,":[31],"we":[32,70,101],"propose":[33],"a":[34,82,90,96],"novel":[35],"augmentation":[36],"method":[37],"using":[46],"distant":[47,64,133],"supervision":[48,134],"over":[49,120,128],"parallel":[50,112],"corpus.":[51,113],"However,":[52],"there":[53],"mislabeled":[56],"unlabeled":[58],"words":[61],"inevitably":[62],"in":[63,111],"supervision.":[65],"To":[66],"address":[67],"problem,":[69],"take":[71],"advantage":[72],"memorization":[75],"effects":[76],"deep":[78],"neural":[79],"networks":[80],"small":[83],"annotated":[86,137],"get":[89],"model":[91,104,118,126],"with":[92],"much":[93],"knowledge":[94],"little":[97],"noise,":[98],"then":[100],"use":[102],"relabel":[106],"sentences":[110],"Experiments":[114],"show":[115],"that":[116],"trained":[119,127],"relabeled":[122],"outperforms":[124],"generated":[131],"from":[132],"data.":[138],"Our":[139],"code":[140],"available":[142],"at":[143],"https://github.com/farlit/ACDS.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}