{"total":16,"rows":[{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148,"area":null},{"id":"2104.05596","title":"Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages","created":"2021-04-12","cited_by_count":136,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2403.06350","title":"IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages","created":"2024-03-11","cited_by_count":52,"area":null},{"id":"2109.02903","title":"IndicBART: A Pre-trained Model for Indic Natural Language Generation","created":"2021-09-07","cited_by_count":39,"area":null},{"id":"2107.10181","title":"Debiasing Multilingual Word Embeddings: A Case Study of Three Indian Languages","created":"2021-07-21","cited_by_count":8,"area":null},{"id":"2209.13279","title":"Improving Multilingual Neural Machine Translation System for Indic Languages","created":"2022-09-27","cited_by_count":6,"area":null},{"id":"2310.09765","title":"MILPaC: A Novel Benchmark for Evaluating Translation of Legal Text to Indian Languages","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2107.04512","title":"Using Machine Translation to Localize Task Oriented NLG Output","created":"2021-07-09","cited_by_count":1,"area":null},{"id":"2203.16127","title":"An Overview of Indian Language Datasets used for Text Summarization","created":"2022-03-30","cited_by_count":1,"area":null},{"id":"2411.19096","title":"Pralekha: Cross-Lingual Document Alignment for Indic Languages","created":"2024-11-28","cited_by_count":1,"area":null},{"id":"2509.19941","title":"CorIL: Towards Enriching Indian Language to Indian Language Parallel Corpora and Machine Translation Systems","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2511.00486","title":"Leveraging the Cross-Domain & Cross-Linguistic Corpus for Low Resource NMT: A Case Study On Bhili-Hindi-English Parallel Corpus","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2412.15471","title":"A Review of the Marathi Natural Language Processing","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2512.18593","title":"From Scratch to Fine-Tuned: A Comparative Study of Transformer Training Strategies for Legal Machine Translation","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2605.27050","title":"BhashaSetu: A Data-Centric Approach to Low-Resource Machine Translation","created":"2026-05-26","cited_by_count":0,"area":null}],"next_cursor":null}