{"id":"https://openalex.org/W2949884065","doi":"https://doi.org/10.18653/v1/p19-1075","title":"ChID: A Large-scale Chinese IDiom Dataset for Cloze Test","display_name":"ChID: A Large-scale Chinese IDiom Dataset for Cloze Test","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2949884065","doi":"https://doi.org/10.18653/v1/p19-1075","mag":"2949884065"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1075","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1075","pdf_url":"https://www.aclweb.org/anthology/P19-1075.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1075.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016924921","display_name":"Chujie Zheng","orcid":"https://orcid.org/0000-0002-7364-972X"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]},{"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":true,"raw_author_name":"Chujie Zheng","raw_affiliation_strings":["Dept. of Physics, Tsinghua University, Beijing 100084, China","Beijing National Research Center for Information Science and Technology, China","Institute for Artificial Intelligence, Dept. of Computer Science, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Dept. of Physics, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Institute for Artificial Intelligence, Dept. of Computer Science, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044042138","display_name":"Minlie Huang","orcid":"https://orcid.org/0000-0001-7111-1849"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]},{"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":"Minlie Huang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, China","Institute for Artificial Intelligence, Dept. of Computer Science, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Institute for Artificial Intelligence, Dept. of Computer Science, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100618738","display_name":"Aixin Sun","orcid":"https://orcid.org/0000-0003-0764-4258"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Aixin Sun","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016924921"],"corresponding_institution_ids":["https://openalex.org/I4210156423","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":5.3471,"has_fulltext":true,"cited_by_count":57,"citation_normalized_percentile":{"value":0.96495893,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"778","last_page":"787"},"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":0.9998000264167786,"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/T13629","display_name":"Text Readability and Simplification","score":0.9908000230789185,"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":0.7827984094619751},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.730657696723938},{"id":"https://openalex.org/keywords/cloze-test","display_name":"Cloze test","score":0.6347354650497437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6260290145874023},{"id":"https://openalex.org/keywords/reading-comprehension","display_name":"Reading comprehension","score":0.6073156595230103},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5904026031494141},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49584874510765076},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.48642659187316895},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4797954857349396},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.46002450585365295},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.45946383476257324},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.456562876701355},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4241308271884918},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3404415249824524},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.05616137385368347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827984094619751},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.730657696723938},{"id":"https://openalex.org/C2779286901","wikidata":"https://www.wikidata.org/wiki/Q951968","display_name":"Cloze test","level":4,"score":0.6347354650497437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6260290145874023},{"id":"https://openalex.org/C2778780117","wikidata":"https://www.wikidata.org/wiki/Q3269423","display_name":"Reading comprehension","level":3,"score":0.6073156595230103},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5904026031494141},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49584874510765076},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.48642659187316895},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4797954857349396},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46002450585365295},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.45946383476257324},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.456562876701355},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4241308271884918},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3404415249824524},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.05616137385368347},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1075","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1075","pdf_url":"https://www.aclweb.org/anthology/P19-1075.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1075","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1075","pdf_url":"https://www.aclweb.org/anthology/P19-1075.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8799999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6153920497","display_name":null,"funder_award_id":"61876096","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949884065.pdf","grobid_xml":"https://content.openalex.org/works/W2949884065.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W406530407","https://openalex.org/W853935626","https://openalex.org/W1502101714","https://openalex.org/W1508106516","https://openalex.org/W1522301498","https://openalex.org/W1544827683","https://openalex.org/W1554663460","https://openalex.org/W1579929927","https://openalex.org/W1614298861","https://openalex.org/W1975879668","https://openalex.org/W2006953227","https://openalex.org/W2025357764","https://openalex.org/W2064675550","https://openalex.org/W2125361831","https://openalex.org/W2126209950","https://openalex.org/W2133564696","https://openalex.org/W2165805036","https://openalex.org/W2170157806","https://openalex.org/W2250774661","https://openalex.org/W2270070752","https://openalex.org/W2473344385","https://openalex.org/W2551396370","https://openalex.org/W2606964149","https://openalex.org/W2692059227","https://openalex.org/W2804552794","https://openalex.org/W2805766422","https://openalex.org/W2889048825","https://openalex.org/W2949615363","https://openalex.org/W2951534261","https://openalex.org/W2953384591","https://openalex.org/W2962809918","https://openalex.org/W2963015836","https://openalex.org/W2963344337","https://openalex.org/W2963681467","https://openalex.org/W2963685900","https://openalex.org/W2963748441","https://openalex.org/W2963956494","https://openalex.org/W2963957489","https://openalex.org/W2964121744","https://openalex.org/W2964223283","https://openalex.org/W2964267515","https://openalex.org/W2964308564","https://openalex.org/W3104486441","https://openalex.org/W4238565770","https://openalex.org/W4301002347","https://openalex.org/W4391156274"],"related_works":["https://openalex.org/W2082296339","https://openalex.org/W2030403248","https://openalex.org/W2161828220","https://openalex.org/W1972348076","https://openalex.org/W2759069336","https://openalex.org/W2094703246","https://openalex.org/W1487749556","https://openalex.org/W2778521539","https://openalex.org/W4214887841","https://openalex.org/W3208785854"],"abstract_inverted_index":{"Cloze-style":[0],"reading":[1],"comprehension":[2,30],"in":[3,37,44],"Chinese":[4,22],"is":[5,90],"still":[6],"limited":[7],"due":[8],"to":[9,57],"the":[10,29,42,53,68,74,79,87],"lack":[11],"of":[12,31,70,76,81,95],"various":[13],"corpora.":[14],"In":[15,39],"this":[16,40],"paper":[17],"we":[18],"propose":[19],"a":[20,33,45,98],"large-scale":[21],"cloze":[23],"test":[24],"dataset":[25],"ChID,":[26],"which":[27],"studies":[28],"idiom,":[32],"unique":[34],"language":[35],"phenomenon":[36],"Chinese.":[38],"corpus,":[41],"idioms":[43,72,77],"passage":[46],"are":[47],"replaced":[48],"by":[49],"blank":[50],"symbols":[51],"and":[52,73],"correct":[54],"answer":[55],"needs":[56],"be":[58],"chosen":[59],"from":[60],"well-designed":[61],"candidate":[62,71],"idioms.":[63],"We":[64],"carefully":[65],"study":[66],"how":[67],"design":[69],"representation":[75],"affect":[78],"performance":[80],"state-of-the-art":[82],"models.":[83],"Results":[84],"show":[85],"that":[86,94],"machine":[88],"accuracy":[89],"substantially":[91],"worse":[92],"than":[93],"human,":[96],"indicating":[97],"large":[99],"space":[100],"for":[101],"further":[102],"research.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":10}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
