{"id":"https://openalex.org/W4400066957","doi":"https://doi.org/10.1145/3663976.3664020","title":"PDA: Data Augmentation with Preposition Words on Chinese textclassification","display_name":"PDA: Data Augmentation with Preposition Words on Chinese textclassification","publication_year":2024,"publication_date":"2024-04-26","ids":{"openalex":"https://openalex.org/W4400066957","doi":"https://doi.org/10.1145/3663976.3664020"},"language":"en","primary_location":{"id":"doi:10.1145/3663976.3664020","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3663976.3664020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 2nd Asia Conference on Computer Vision, Image Processing and Pattern Recognition","raw_type":"proceedings-article"},"type":"conference-paper","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/A5076187792","display_name":"Leixin Yang","orcid":"https://orcid.org/0000-0001-6945-9571"},"institutions":[{"id":"https://openalex.org/I120825670","display_name":"Yunnan Normal University","ror":"https://ror.org/00sc9n023","country_code":"CN","type":"education","lineage":["https://openalex.org/I120825670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leixin Yang","raw_affiliation_strings":["School of Information Science and Technology, Yunnan Normal University, China"],"raw_orcid":"https://orcid.org/0000-0001-6945-9571","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Yunnan Normal University, China","institution_ids":["https://openalex.org/I120825670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104123870","display_name":"Haoyu Xiong","orcid":"https://orcid.org/0009-0002-5972-9405"},"institutions":[{"id":"https://openalex.org/I120825670","display_name":"Yunnan Normal University","ror":"https://ror.org/00sc9n023","country_code":"CN","type":"education","lineage":["https://openalex.org/I120825670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Xiong","raw_affiliation_strings":["School of Information Science and Technology, Yunnan Normal University, China"],"raw_orcid":"https://orcid.org/0009-0009-9627-9010","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Yunnan Normal University, China","institution_ids":["https://openalex.org/I120825670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027810378","display_name":"Yu Xiang","orcid":"https://orcid.org/0000-0003-4430-8640"},"institutions":[{"id":"https://openalex.org/I120825670","display_name":"Yunnan Normal University","ror":"https://ror.org/00sc9n023","country_code":"CN","type":"education","lineage":["https://openalex.org/I120825670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Xiang","raw_affiliation_strings":["School of Information Science and Technology, Yunnan Normal University, China"],"raw_orcid":"https://orcid.org/0000-0003-4430-8640","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Yunnan Normal University, China","institution_ids":["https://openalex.org/I120825670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I120825670"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.998199999332428,"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":0.9832000136375427,"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":0.6859664916992188},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6110426783561707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37172356247901917},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3412780165672302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6859664916992188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6110426783561707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37172356247901917},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3412780165672302},{"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:10.1145/3663976.3664020","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3663976.3664020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 2nd Asia Conference on Computer Vision, Image Processing and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4399999976158142,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2170872814","https://openalex.org/W2952370363","https://openalex.org/W3174864715","https://openalex.org/W4226150360"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"While":[0],"previous":[1],"data":[2,26,116],"augmentation":[3,27,117],"methods":[4],"have":[5,12],"shown":[6],"good":[7],"results,":[8],"some":[9],"of":[10,36,96,113],"them":[11],"limitations":[13],"in":[14,94],"applicability":[15],"and":[16,65,91,107],"complexity.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21],"propose":[22],"a":[23,83],"simple":[24],"Chinese":[25,44,77,104],"technique":[28],"called":[29],"Preposition":[30],"Data":[31],"Augmentation":[32],"(PDA).":[33],"The":[34,50],"principle":[35],"PDA":[37,80,115],"is":[38],"straightforward,":[39],"which":[40],"involves":[41],"randomly":[42],"inserting":[43],"prepositions":[45],"into":[46],"the":[47,54,58,62,68,108,111],"original":[48,59],"sentences.":[49],"augmented":[51],"samples":[52],"maintain":[53],"same":[55],"order":[56],"as":[57],"ones,":[60],"preserving":[61],"semantic":[63],"information":[64],"retaining":[66],"all":[67],"input":[69],"information.":[70],"According":[71],"to":[72],"our":[73,79,114],"experimental":[74],"results":[75,109],"on":[76,102],"datasets,":[78],"method":[81],"demonstrates":[82],"certain":[84],"advantage":[85],"over":[86],"AEDA":[87],"[5],":[88],"EDA":[89],"[13],":[90],"back-translation":[92],"[11]":[93],"terms":[95],"model":[97],"generalization.":[98],"We":[99],"conducted":[100],"experiments":[101],"various":[103],"classification":[105],"tasks,":[106],"indicate":[110],"advantages":[112],"method.":[118]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}