{"id":"https://openalex.org/W4412889187","doi":"https://doi.org/10.18653/v1/2025.bea-1.68","title":"EduCSW: Building a Mandarin-English Code-Switched Generation Pipeline for Computer Science Learning","display_name":"EduCSW: Building a Mandarin-English Code-Switched Generation Pipeline for Computer Science Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889187","doi":"https://doi.org/10.18653/v1/2025.bea-1.68"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.bea-1.68","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.68","pdf_url":"https://aclanthology.org/2025.bea-1.68.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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.bea-1.68.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ruishi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruishi Chen","raw_affiliation_strings":["Stanford University Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100950747","display_name":"Yiling Zhao","orcid":"https://orcid.org/0000-0002-1374-4952"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiling Zhao","raw_affiliation_strings":["Stanford University Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21791585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"908","last_page":"919"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.7103999853134155,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11122","display_name":"Online Learning and Analytics","score":0.7103999853134155,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/pipeline","display_name":"Pipeline (software)","score":0.7717860341072083},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7527170777320862},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7290268540382385},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5173201560974121},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.33556726574897766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33263063430786133},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09994325041770935}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7717860341072083},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7527170777320862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7290268540382385},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5173201560974121},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33556726574897766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33263063430786133},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09994325041770935},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.bea-1.68","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.68","pdf_url":"https://aclanthology.org/2025.bea-1.68.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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.bea-1.68","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.68","pdf_url":"https://aclanthology.org/2025.bea-1.68.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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889187.pdf","grobid_xml":"https://content.openalex.org/works/W4412889187.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"EduCSW,":[3],"a":[4,55,75,92],"novel":[5],"pipeline":[6,115],"for":[7,58,119],"generating":[8,120],"Mandarin-English":[9,104],"codeswitched":[10],"text":[11,44,90],"to":[12,22,106,123],"support":[13,124],"AI-powered":[14],"educational":[15,128],"tools":[16,129],"that":[17,40],"adapt":[18],"computer":[19,59],"science":[20,60],"instruction":[21],"learners'":[23],"language":[24,110],"proficiency":[25],"through":[26],"mixed-language":[27],"delivery.To":[28],"address":[29],"the":[30,85,117,125],"scarcity":[31],"of":[32,66,96,127],"code-mixed":[33,49],"datasets,":[34],"we":[35],"propose":[36],"an":[37],"encoder-decoder":[38],"architecture":[39],"generates":[41],"natural":[42],"code-switched":[43],"using":[45],"only":[46],"minimal":[47],"existing":[48],"examples":[50],"and":[51,84,112],"parallel":[52],"corpora.Evaluated":[53],"on":[54],"corpus":[56],"curated":[57],"education,":[61],"human":[62],"annotators":[63],"rated":[64],"60-64%":[65],"our":[67],"model's":[68],"outputs":[69],"as":[70],"natural,":[71],"significantly":[72],"outperforming":[73],"both":[74],"baseline":[76],"fine-tuned":[77],"neural":[78],"machine":[79],"translation":[80],"(NMT)":[81],"model":[82,87],"(22-24%)":[83],"DeepSeek-R1":[86],"(34-44%).The":[88],"generated":[89],"achieves":[91],"Code-Mixing":[93],"Index":[94],"(CMI)":[95],"25.28%,":[97],"aligning":[98],"with":[99,130],"patterns":[100],"observed":[101],"in":[102],"spontaneous":[103],"code-switching.Designed":[105],"be":[107],"generalizable":[108],"across":[109],"pairs":[111],"domains,":[113],"this":[114],"lays":[116],"groundwork":[118],"training":[121],"data":[122],"development":[126],"dynamic":[131],"code-switching":[132],"capabilities.":[133]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}