{"total":75,"rows":[{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"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":"2301.01967","title":"A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies","created":"2023-01-05","cited_by_count":59,"area":null},{"id":"2104.00235","title":"Multilingual and code-switching ASR challenges for low resource Indian languages","created":"2021-04-01","cited_by_count":53,"area":null},{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"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":"2103.09593","title":"Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots","created":"2021-03-17","cited_by_count":23,"area":null},{"id":"2206.02093","title":"LAE: Language-Aware Encoder for Monolingual and Multilingual ASR","created":"2022-06-05","cited_by_count":22,"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":"2206.14580","title":"Language-specific Characteristic Assistance for Code-switching Speech Recognition","created":"2022-06-29","cited_by_count":20,"area":null},{"id":"2111.15016","title":"Joint Modeling of Code-Switched and Monolingual ASR via Conditional Factorization","created":"2021-11-29","cited_by_count":18,"area":null},{"id":"2107.01573","title":"Arabic Code-Switching Speech Recognition using Monolingual Data","created":"2021-07-04","cited_by_count":17,"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":"2102.01051","title":"SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification","created":"2021-02-01","cited_by_count":11,"area":null},{"id":"2406.06263","title":"MaskLID: Code-Switching Language Identification through Iterative Masking","created":"2024-06-10","cited_by_count":11,"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":"2309.15674","title":"Speech collage: code-switched audio generation by collaging monolingual corpora","created":"2023-09-27","cited_by_count":10,"area":null},{"id":"2310.02629","title":"BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition","created":"2023-10-04","cited_by_count":9,"area":"moe"},{"id":"2106.06004","title":"CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing","created":"2021-06-10","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":"2305.16724","title":"Code-Switched Text Synthesis in Unseen Language Pairs","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2309.11327","title":"Leveraging Data Collection and Unsupervised Learning for Code-switched Tunisian Arabic Automatic Speech Recognition","created":"2023-09-20","cited_by_count":7,"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":"2505.14469","title":"Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations","created":"2025-05-20","cited_by_count":6,"area":"safety"},{"id":"2102.12407","title":"Task-Specific Pre-Training and Cross Lingual Transfer for Code-Switched Data","created":"2021-02-24","cited_by_count":5,"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":"2211.16319","title":"Benchmarking Evaluation Metrics for Code-Switching Automatic Speech Recognition","created":"2022-11-22","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":"2501.13419","title":"A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions","created":"2025-01-23","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":"2104.06268","title":"Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling","created":"2021-04-13","cited_by_count":4,"area":null},{"id":"2310.15258","title":"Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention","created":"2023-10-23","cited_by_count":4,"area":"lr"},{"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":"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":"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":"2402.01505","title":"Code-Switched Language Identification is Harder Than You Think","created":"2024-02-02","cited_by_count":3,"area":null},{"id":"2406.18120","title":"ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs","created":"2024-06-26","cited_by_count":3,"area":null},{"id":"2512.10967","title":"ASR Under the Stethoscope: Evaluating Biases in Clinical Speech Recognition across Indian Languages","created":"2025-11-30","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":"2112.06462","title":"Predicting User Code-Switching Level from Sociological and Psychological Profiles","created":"2021-12-13","cited_by_count":2,"area":null},{"id":"2205.06118","title":"Findings of the Shared Task on Offensive Span Identification from Code-Mixed Tamil-English Comments","created":"2022-05-12","cited_by_count":2,"area":null},{"id":"2409.02050","title":"Enhancing Code-Switching Speech Recognition with LID-Based Collaborative Mixture of Experts Model","created":"2024-09-03","cited_by_count":2,"area":"moe"},{"id":"2412.12761","title":"Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detection","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2106.05885","title":"Balanced End-to-End Monolingual pre-training for Low-Resourced Indic Languages Code-Switching Speech Recognition","created":"2021-06-10","cited_by_count":1,"area":null},{"id":"2208.00433","title":"The Who in Code-Switching: A Case Study for Predicting Egyptian Arabic-English Code-Switching Levels based on Character Profiles","created":"2022-07-31","cited_by_count":1,"area":null},{"id":"2305.14534","title":"Detecting Propaganda Techniques in Code-Switched Social Media Text","created":"2023-05-23","cited_by_count":1,"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":"2503.21530","title":"Low-Resource Transliteration for Roman-Urdu and Urdu Using Transformer-Based Models","created":"2025-03-27","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":"2504.13284","title":"Sentiment Analysis on the young people's perception about the mobile Internet costs in Senegal","created":"2025-04-17","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":"2609.01016","title":"Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2105.09226","title":"Detection of Emotions in Hindi-English Code Mixed Text Data","created":"2021-05-19","cited_by_count":0,"area":null},{"id":"2106.07699","title":"Using heterogeneity in semi-supervised transcription hypotheses to improve code-switched speech recognition","created":"2021-06-14","cited_by_count":0,"area":null},{"id":"2206.09765","title":"Bilingual by default: Voice Assistants and the role of code-switching in creating a bilingual user experience","created":"2022-06-20","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":"2403.08011","title":"Gujarati-English Code-Switching Speech Recognition using ensemble prediction of spoken language","created":"2024-03-12","cited_by_count":0,"area":null},{"id":"2411.08294","title":"Collaborative Participatory Research with LLM Agents in South Asia: An Empirically-Grounded Methodological Initiative and Agenda from Field Evidence in Sri Lanka","created":"2024-11-13","cited_by_count":0,"area":"agents"},{"id":"2505.16631","title":"MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queries","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2511.20106","title":"EM2LDL: A Multilingual Speech Corpus for Mixed Emotion Recognition through Label Distribution Learning","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2602.23388","title":"Task-Lens: Cross-Task Utility Based Speech Dataset Profiling for Low-Resource Indian Languages","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.16184","title":"Polyglot-Lion: Efficient Multilingual ASR for Singapore via Balanced Fine-Tuning of Qwen3-ASR","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.26587","title":"EnTaCs: Analyzing the Relationship Between Sentiment and Language Choice in English-Tamil Code-Switching","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2606.13537","title":"When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.26901","title":"SamaVaani: Auditing and Debiasing Multilingual Clinical ASR for Indian Languages","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.02757","title":"Reinforcement Learning for Data-Efficient Code-Switched ASR","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.15861","title":"Conditional Reliability of Toxicity Signals for Multilingual and Code-Mixed Abuse Detection","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2609.11786","title":"Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English Yoruba Code-Switched Speech","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2610.08303","title":"Language Unalignability: Why Some Concepts Resist Cross-Cultural Benchmark Evaluation","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.20327","title":"Anuvani-Diarization: Zero Shot Speaker Diarization and Annotation Conventions Across 22 Languages","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}