{"id":"https://openalex.org/W4320066596","doi":"https://doi.org/10.1145/3568739.3568801","title":"On the Construction of Knowledge-Communication-Oriented Computer Spoken Corpus for Endangered Languages","display_name":"On the Construction of Knowledge-Communication-Oriented Computer Spoken Corpus for Endangered Languages","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4320066596","doi":"https://doi.org/10.1145/3568739.3568801"},"language":"en","primary_location":{"id":"doi:10.1145/3568739.3568801","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3568739.3568801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on Digital Technology in Education","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/A5075101313","display_name":"Zihui Xiao","orcid":"https://orcid.org/0000-0002-5940-7118"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zihui Xiao","raw_affiliation_strings":["Jinan University, China"],"raw_orcid":"https://orcid.org/0000-0002-5940-7118","affiliations":[{"raw_affiliation_string":"Jinan University, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058110730","display_name":"Fan Jun-jun","orcid":"https://orcid.org/0000-0002-5791-9451"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjun Fan","raw_affiliation_strings":["Jinan University, China"],"raw_orcid":"https://orcid.org/0000-0002-5791-9451","affiliations":[{"raw_affiliation_string":"Jinan University, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084132742","display_name":"Wei Gao","orcid":"https://orcid.org/0000-0002-0140-7561"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Gao","raw_affiliation_strings":["South China University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-0140-7561","affiliations":[{"raw_affiliation_string":"South China University of Technology, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075101313"],"corresponding_institution_ids":["https://openalex.org/I159948400"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17192778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"369","last_page":"374"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9882000088691711,"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/T12031","display_name":"Speech and dialogue systems","score":0.9642999768257141,"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":0.8312257528305054},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.6932900547981262},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6908889412879944},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6174662113189697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6160503625869751},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.5273759365081787},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4832964241504669},{"id":"https://openalex.org/keywords/lingua-franca","display_name":"Lingua franca","score":0.4130837917327881},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3053535521030426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8312257528305054},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.6932900547981262},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6908889412879944},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6174662113189697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6160503625869751},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.5273759365081787},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4832964241504669},{"id":"https://openalex.org/C159789966","wikidata":"https://www.wikidata.org/wiki/Q80839","display_name":"Lingua franca","level":2,"score":0.4130837917327881},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3053535521030426},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3568739.3568801","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3568739.3568801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on Digital Technology in Education","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W85752199","https://openalex.org/W1575460932","https://openalex.org/W2104630935","https://openalex.org/W2154124206","https://openalex.org/W2559204922","https://openalex.org/W2798275418","https://openalex.org/W4232537392"],"related_works":["https://openalex.org/W2375537499","https://openalex.org/W2516977220","https://openalex.org/W3096124370","https://openalex.org/W2794113965","https://openalex.org/W1982878818","https://openalex.org/W2384280299","https://openalex.org/W2366526038","https://openalex.org/W2183648197","https://openalex.org/W99386505","https://openalex.org/W3087106119"],"abstract_inverted_index":{"This":[0,76],"Corpus/corpora":[1],"is":[2,14],"a":[3,42],"computer":[4],"database":[5],"that":[6],"stores":[7],"language":[8],"materials.":[9],"Corpus":[10,59],"in":[11],"the":[12,31,51,65,68,72,80,84,91],"world":[13],"dominated":[15],"by":[16],"lingua":[17],"franca":[18],"corpus.":[19],"However,":[20],"these":[21],"corpora":[22],"have":[23],"limited":[24],"samples":[25],"and":[26,71,98],"are":[27],"difficult":[28],"to":[29,40,49],"meet":[30],"needs":[32],"of":[33,53,82,87,93],"machine":[34],"artificial":[35],"intelligence.":[36],"The":[37],"paper":[38,77],"proposes":[39],"build":[41],"Knowledge-Communication-Oriented":[43,57],"spoken":[44,85],"corpus":[45,54,86,94,96,99],"for":[46],"Endangered":[47],"Languages":[48],"enrich":[50],"content":[52],"research.":[55],"A":[56],"Spoken":[58],"was":[60],"divided":[61],"into":[62],"three":[63],"sub-corporas,":[64],"words":[66],"sub-corpu,":[67],"sentences":[69],"sub-corpus,":[70],"narrative":[73],"discourses":[74],"sub-corpus.":[75],"mainly":[78],"introduces":[79],"methods":[81],"constructing":[83],"endangered":[88],"languages":[89],"from":[90],"aspects":[92],"collection,":[95],"arrangement":[97],"annotation.":[100]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
