{"total":35,"rows":[{"id":"2105.13626","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","created":"2021-05-28","cited_by_count":509,"area":null},{"id":"2103.10730","title":"MuRIL: Multilingual Representations for Indian Languages","created":"2021-03-19","cited_by_count":179,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2212.05409","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","created":"2022-12-11","cited_by_count":102,"area":null},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34,"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":"2309.13173","title":"BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP","created":"2023-09-22","cited_by_count":23,"area":null},{"id":"2205.12676","title":"Evaluating the Diversity, Equity and Inclusion of NLP Technology: A Case Study for Indian Languages","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2205.03018","title":"Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users","created":"2022-05-06","cited_by_count":19,"area":null},{"id":"2305.15814","title":"Bhasha-Abhijnaanam: Native-script and romanized Language Identification for 22 Indic languages","created":"2023-05-25","cited_by_count":13,"area":null},{"id":"2601.07220","title":"The Roots of Performance Disparity in Multilingual Language Models: Intrinsic Modeling Difficulty or Design Choices?","created":"2026-01-12","cited_by_count":11,"area":null},{"id":"2306.04530","title":"Lenient Evaluation of Japanese Speech Recognition: Modeling Naturally Occurring Spelling Inconsistency","created":"2023-06-07","cited_by_count":10,"area":null},{"id":"2408.08964","title":"BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis","created":"2024-08-16","cited_by_count":10,"area":null},{"id":"2102.10084","title":"Hate-Alert@DravidianLangTech-EACL2021: Ensembling strategies for Transformer-based Offensive language Detection","created":"2021-02-19","cited_by_count":8,"area":null},{"id":"2407.00416","title":"Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs","created":"2024-06-29","cited_by_count":7,"area":null},{"id":"2108.03886","title":"Do Images really do the Talking? Analysing the significance of Images in Tamil Troll meme classification","created":"2021-08-09","cited_by_count":6,"area":null},{"id":"2410.21321","title":"User-Aware Multilingual Abusive Content Detection in Social Media","created":"2024-10-26","cited_by_count":6,"area":null},{"id":"2501.00529","title":"Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches","created":"2024-12-31","cited_by_count":6,"area":null},{"id":"2407.04459","title":"Generalists vs. Specialists: Evaluating Large Language Models for Urdu","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2108.10939","title":"Towards Offensive Language Identification for Tamil Code-Mixed YouTube Comments and Posts","created":"2021-08-24","cited_by_count":4,"area":null},{"id":"2501.05816","title":"IndoNLP 2025: Shared Task on Real-Time Reverse Transliteration for Romanized Indo-Aryan languages","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2507.04793","title":"A Survey of Pun Generation: Datasets, Evaluations and Methodologies","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2106.12698","title":"Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction","created":"2021-06-24","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":"2303.03457","title":"Spelling convention sensitivity in neural language models","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2311.07804","title":"IruMozhi: Automatically classifying diglossia in Tamil","created":"2023-11-13","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":"2504.21540","title":"Improving Informally Romanized Language Identification","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2511.22769","title":"Modeling Romanized Hindi and Bengali: Dataset Creation and Multilingual LLM Integration","created":"2025-11-27","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":"2312.13614","title":"Structure-Aware Path Inference for Neural Finite State Transducers","created":"2023-12-21","cited_by_count":0,"area":null},{"id":"2505.19851","title":"Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2601.02906","title":"Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.14958","title":"Script Sensitivity: Benchmarking Language Models on Unicode, Romanized and Mixed-Script Sinhala","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2609.01788","title":"VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}