{"total":18,"rows":[{"id":"2204.08398","title":"L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models","created":"2022-04-18","cited_by_count":34,"area":null},{"id":"2101.10524","title":"El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing","created":"2021-01-26","cited_by_count":8,"area":null},{"id":"2109.04733","title":"Genre as Weak Supervision for Cross-lingual Dependency Parsing","created":"2021-09-10","cited_by_count":8,"area":null},{"id":"2405.05572","title":"From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2104.08578","title":"GupShup: An Annotated Corpus for Abstractive Summarization of Open-Domain Code-Switched Conversations","created":"2021-04-17","cited_by_count":5,"area":null},{"id":"2111.01231","title":"Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2211.07514","title":"CST5: Data Augmentation for Code-Switched Semantic Parsing","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2204.10621","title":"Out-of-Domain Evaluation of Finnish Dependency Parsing","created":"2022-04-22","cited_by_count":2,"area":null},{"id":"2506.07274","title":"Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource Languages","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2401.16403","title":"ViLexNorm: A Lexical Normalization Corpus for Vietnamese Social Media Text","created":"2024-01-29","cited_by_count":1,"area":null},{"id":"2403.01364","title":"Improving Cross-lingual Representation for Semantic Retrieval with Code-switching","created":"2024-03-03","cited_by_count":1,"area":null},{"id":"2409.20467","title":"A Weakly Supervised Data Labeling Framework for Machine Lexical Normalization in Vietnamese Social Media","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2503.07990","title":"Enhancing Multilingual Language Models for Code-Switched Input Data","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2601.16623","title":"MultiLexNorm++: A Unified Benchmark and a Generative Model for Lexical Normalization for Asian Languages","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2206.09167","title":"MANorm: A Normalization Dictionary for Moroccan Arabic Dialect Written in Latin Script","created":"2022-06-18","cited_by_count":0,"area":null},{"id":"2207.03256","title":"Part-of-Speech Tagging of Odia Language Using statistical and Deep Learning-Based Approaches","created":"2022-07-07","cited_by_count":0,"area":null},{"id":"2309.13561","title":"Cordyceps@LT-EDI: Patching Language-Specific Homophobia/Transphobia Classifiers with a Multilingual Understanding","created":"2023-09-24","cited_by_count":0,"area":null},{"id":"2602.06307","title":"Lost in Speech: Benchmarking, Evaluation, and Parsing of Spoken Bilingual Conversational Language Beyond Standard UD Assumptions","created":"2026-02-06","cited_by_count":0,"area":null}],"next_cursor":null}