{"total":37,"rows":[{"id":"2212.09660","title":"The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges","created":"2022-12-19","cited_by_count":35,"area":null},{"id":"2107.03760","title":"HinGE: A Dataset for Generation and Evaluation of Code-Mixed Hinglish Text","created":"2021-07-08","cited_by_count":28,"area":null},{"id":"2106.10123","title":"Challenges and Limitations with the Metrics Measuring the Complexity of Code-Mixed Text","created":"2021-06-18","cited_by_count":18,"area":null},{"id":"2105.08807","title":"Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixing","created":"2021-05-18","cited_by_count":16,"area":null},{"id":"2310.20470","title":"Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation","created":"2023-10-31","cited_by_count":16,"area":null},{"id":"2211.12000","title":"ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic - English","created":"2022-11-22","cited_by_count":13,"area":null},{"id":"2406.07424","title":"MINERS: Multilingual Language Models as Semantic Retrievers","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2507.18791","title":"CodeMixBench: Evaluating Code-Mixing Capabilities of LLMs Across 18 Languages","created":"2025-07-24","cited_by_count":10,"area":null},{"id":"2202.09625","title":"CALCS 2021 Shared Task: Machine Translation for Code-Switched Data","created":"2022-02-19","cited_by_count":9,"area":null},{"id":"2210.12540","title":"EntityCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching","created":"2022-10-22","cited_by_count":8,"area":null},{"id":"2107.11534","title":"MIPE: A Metric Independent Pipeline for Effective Code-Mixed NLG Evaluation","created":"2021-07-24","cited_by_count":7,"area":null},{"id":"2108.01861","title":"Quality Evaluation of the Low-Resource Synthetically Generated Code-Mixed Hinglish Text","created":"2021-08-04","cited_by_count":7,"area":null},{"id":"2210.06990","title":"Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2301.08937","title":"Exploring Methods for Building Dialects-Mandarin Code-Mixing Corpora: A Case Study in Taiwanese Hokkien","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2410.11079","title":"Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilities","created":"2024-10-14","cited_by_count":7,"area":null},{"id":"2503.21670","title":"COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing","created":"2025-03-27","cited_by_count":7,"area":null},{"id":"2410.15308","title":"LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content","created":"2024-10-20","cited_by_count":6,"area":null},{"id":"2403.16771","title":"Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation","created":"2024-03-25","cited_by_count":5,"area":null},{"id":"2106.07823","title":"Challenges and Considerations with Code-Mixed NLP for Multilingual Societies","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2405.12929","title":"Code-mixed Sentiment and Hate-speech Prediction","created":"2024-05-21","cited_by_count":4,"area":null},{"id":"2503.04797","title":"Parallel Corpora for Machine Translation in Low-resource Indic Languages: A Comprehensive Review","created":"2025-03-02","cited_by_count":4,"area":null},{"id":"2206.06141","title":"Am I No Good? Towards Detecting Perceived Burdensomeness and Thwarted Belongingness from Suicide Notes","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2211.07628","title":"Language Agnostic Code-Mixing Data Augmentation by Predicting Linguistic Patterns","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2204.12753","title":"A Comprehensive Understanding of Code-mixed Language Semantics using Hierarchical Transformer","created":"2022-04-27","cited_by_count":2,"area":null},{"id":"2302.11766","title":"MUTANT: A Multi-sentential Code-mixed Hinglish Dataset","created":"2023-02-23","cited_by_count":2,"area":null},{"id":"2309.05270","title":"CONFLATOR: Incorporating Switching Point based Rotatory Positional Encodings for Code-Mixed Language Modeling","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2210.11670","title":"SIT at MixMT 2022: Fluent Translation Built on Giant Pre-trained Models","created":"2022-10-21","cited_by_count":1,"area":null},{"id":"2210.12215","title":"Gui at MixMT 2022 : English-Hinglish: An MT approach for translation of code mixed data","created":"2022-10-21","cited_by_count":1,"area":null},{"id":"2601.17277","title":"PingPong: A Natural Benchmark for Multi-Turn Code-Switching Dialogues","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2206.08053","title":"JU_NLP at HinglishEval: Quality Evaluation of the Low-Resource Code-Mixed Hinglish Text","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2208.03713","title":"Study of Encoder-Decoder Architectures for Code-Mix Search Query Translation","created":"2022-08-07","cited_by_count":0,"area":null},{"id":"2210.11309","title":"The University of Edinburgh's Submission to the WMT22 Code-Mixing Shared Task (MixMT)","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2210.17463","title":"Domain Curricula for Code-Switched MT at MixMT 2022","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2504.21026","title":"Creating and Evaluating Code-Mixed Nepali-English and Telugu-English Datasets for Abusive Language Detection Using Traditional and Deep Learning Models","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2601.16217","title":"ChiEngMixBench: Evaluating Large Language Models on Expert-Style Chinese-English Terminology Mixing","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2603.19771","title":"Neither Here Nor There: Cross-Lingual Representation Dynamics of Code-Mixed Text in Multilingual Encoders","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2607.23242","title":"IndicTalk: A Large-Scale Persona-Based Multilingual Conversational Corpus for Indic Languages","created":"2026-07-25","cited_by_count":0,"area":null}],"next_cursor":null}