{"total":34,"rows":[{"id":"2211.11418","title":"L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages","created":"2022-11-21","cited_by_count":35,"area":null},{"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":"2405.20628","title":"ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos","created":"2024-05-31","cited_by_count":10,"area":null},{"id":"2403.00794","title":"Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models","created":"2024-02-23","cited_by_count":9,"area":null},{"id":"2310.18023","title":"SentMix-3L: A Bangla-English-Hindi Code-Mixed Dataset for Sentiment Analysis","created":"2023-10-27","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":"2310.18387","title":"OffMix-3L: A Novel Code-Mixed Dataset in Bangla-English-Hindi for Offensive Language Identification","created":"2023-10-27","cited_by_count":5,"area":null},{"id":"2510.07037","title":"Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalities","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2309.10272","title":"Mixed-Distil-BERT: Code-mixed Language Modeling for Bangla, English, and Hindi","created":"2023-09-19","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":"2411.05253","title":"What talking you?: Translating Code-Mixed Messaging Texts to English","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2305.15722","title":"Comparative Study of Pre-Trained BERT Models for Code-Mixed Hindi-English Data","created":"2023-05-25","cited_by_count":3,"area":null},{"id":"2410.10580","title":"Multilingual Controlled Generation And Gold-Standard-Agnostic Evaluation of Code-Mixed Sentences","created":"2024-10-14","cited_by_count":3,"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":"2306.14030","title":"My Boli: Code-mixed Marathi-English Corpora, Pretrained Language Models and Evaluation Benchmarks","created":"2023-06-24","cited_by_count":2,"area":null},{"id":"2309.04663","title":"FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning","created":"2023-09-09","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":"2309.16202","title":"Marathi-English Code-mixed Text Generation","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2405.06922","title":"EmoMix-3L: A Code-Mixed Dataset for Bangla-English-Hindi Emotion Detection","created":"2024-05-11","cited_by_count":2,"area":null},{"id":"2505.12587","title":"CMLFormer: A Dual Decoder Transformer with Switching Point Learning for Code-Mixed Language Modeling","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2402.03137","title":"Sociolinguistically Informed Interpretability: A Case Study on Hinglish Emotion Classification","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2505.05063","title":"CodeMixBench: Evaluating Large Language Models on Code Generation with Code-Mixed Prompts","created":"2025-05-08","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":"2604.18423","title":"BhashaSutra: A Task-Centric Unified Survey of Indian NLP Datasets, Corpora, and Resources","created":"2026-04-20","cited_by_count":1,"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":"2306.04964","title":"Leveraging Language Identification to Enhance Code-Mixed Text Classification","created":"2023-06-08","cited_by_count":0,"area":null},{"id":"2312.01103","title":"Code-Mixed Text to Speech Synthesis under Low-Resource Constraints","created":"2023-12-02","cited_by_count":0,"area":null},{"id":"2312.10528","title":"Cross-Linguistic Offensive Language Detection: BERT-Based Analysis of Bengali, Assamese, & Bodo Conversational Hateful Content from Social Media","created":"2023-12-16","cited_by_count":0,"area":null},{"id":"2404.04525","title":"IITK at SemEval-2024 Task 10: Who is the speaker? Improving Emotion Recognition and Flip Reasoning in Conversations via Speaker Embeddings","created":"2024-04-06","cited_by_count":0,"area":null},{"id":"2412.16614","title":"Automated Classification of Cybercrime Complaints using Transformer-based Language Models for Hinglish Texts","created":"2024-12-21","cited_by_count":0,"area":null},{"id":"2506.00332","title":"Disentangling Codemixing in Chats: The NUS ABC Codemixed Corpus","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2509.02514","title":"Comparative Study of Pre-Trained BERT and Large Language Models for Code-Mixed Named Entity Recognition","created":"2025-09-02","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":"2607.25581","title":"Evaluation of forced alignment of code-mixed speech: the case of Hindi-English","created":"2026-07-28","cited_by_count":0,"area":null}],"next_cursor":null}