{"total":53,"rows":[{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92,"area":null},{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2103.13309","title":"Are Multilingual Models Effective in Code-Switching?","created":"2021-03-24","cited_by_count":56,"area":null},{"id":"2303.13592","title":"Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages","created":"2023-03-23","cited_by_count":51,"area":null},{"id":"2112.06223","title":"ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation","created":"2021-12-12","cited_by_count":44,"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":"2107.06483","title":"From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text","created":"2021-07-14","cited_by_count":29,"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":"2304.14535","title":"Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization","created":"2023-04-27","cited_by_count":28,"area":null},{"id":"2103.09593","title":"Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots","created":"2021-03-17","cited_by_count":23,"area":null},{"id":"2105.04846","title":"Can You Traducir This? Machine Translation for Code-Switched Input","created":"2021-05-11","cited_by_count":21,"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":"2410.02381","title":"MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences","created":"2024-10-03","cited_by_count":15,"area":null},{"id":"2111.10962","title":"Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triples","created":"2021-11-22","cited_by_count":13,"area":null},{"id":"2105.13573","title":"Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translation","created":"2021-05-28","cited_by_count":10,"area":null},{"id":"2201.02550","title":"Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition","created":"2022-01-07","cited_by_count":10,"area":null},{"id":"2506.14012","title":"Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text","created":"2025-06-16","cited_by_count":10,"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":"2102.05638","title":"Generating Synthetic Text Data to Evaluate Causal Inference Methods","created":"2021-02-10","cited_by_count":9,"area":null},{"id":"2205.12649","title":"Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation","created":"2022-05-25","cited_by_count":9,"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":"2306.08753","title":"Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer","created":"2023-06-14","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":"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":"2305.16724","title":"Code-Switched Text Synthesis in Unseen Language Pairs","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2403.04872","title":"Code-Mixed Probes Show How Pre-Trained Models Generalise On Code-Switched Text","created":"2024-03-07","cited_by_count":7,"area":null},{"id":"2203.08979","title":"Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2410.22660","title":"Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2210.12214","title":"Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation","created":"2022-10-21","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":"2311.12405","title":"IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languages","created":"2023-11-21","cited_by_count":5,"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":"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":"2411.00691","title":"Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis","created":"2024-11-01","cited_by_count":4,"area":null},{"id":"2507.07741","title":"Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2309.02915","title":"Persona-aware Generative Model for Code-mixed Language","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2310.15262","title":"Data Augmentation Techniques for Machine Translation of Code-Switched Texts: A Comparative Study","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2404.17216","title":"Prompting Towards Alleviating Code-Switched Data Scarcity in Under-Resourced Languages with GPT as a Pivot","created":"2024-04-26","cited_by_count":3,"area":null},{"id":"2503.20007","title":"Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2109.10197","title":"One Source, Two Targets: Challenges and Rewards of Dual Decoding","created":"2021-09-21","cited_by_count":2,"area":null},{"id":"2109.14350","title":"Call Larisa Ivanovna: Code-Switching Fools Multilingual NLU Models","created":"2021-09-29","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":"2309.05044","title":"The Effect of Alignment Objectives on Code-Switching Translation","created":"2023-09-10","cited_by_count":1,"area":null},{"id":"2407.04368","title":"Romanization Encoding For Multilingual ASR","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2407.14295","title":"CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2409.00120","title":"ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2503.23576","title":"The Impact of Code-switched Synthetic Data Quality is Task Dependent: Insights from MT and ASR","created":"2025-03-30","cited_by_count":1,"area":null},{"id":"2506.03593","title":"Is linguistically-motivated data augmentation worth it?","created":"2025-06-04","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":"2108.10561","title":"Taming the Beast: Learning to Control Neural Conversational Models","created":"2021-08-24","cited_by_count":0,"area":null},{"id":"2403.15696","title":"MixRED: A Mix-lingual Relation Extraction Dataset","created":"2024-03-23","cited_by_count":0,"area":null}],"next_cursor":null}