{"total":42,"rows":[{"id":"2309.04662","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset","created":"2023-09-09","cited_by_count":181,"area":null},{"id":"2103.10730","title":"MuRIL: Multilingual Representations for Indian Languages","created":"2021-03-19","cited_by_count":179,"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":"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":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2205.03983","title":"Building Machine Translation Systems for the Next Thousand Languages","created":"2022-05-09","cited_by_count":69,"area":null},{"id":"2205.15960","title":"NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages","created":"2022-05-31","cited_by_count":68,"area":null},{"id":"2109.05125","title":"MURAL: Multimodal, Multitask Retrieval Across Languages","created":"2021-09-10","cited_by_count":44,"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":"2104.00290","title":"Many-to-English Machine Translation Tools, Data, and Pretrained Models","created":"2021-04-01","cited_by_count":31,"area":null},{"id":"2204.08776","title":"IndicXNLI: Evaluating Multilingual Inference for Indian Languages","created":"2022-04-19","cited_by_count":26,"area":null},{"id":"2203.08850","title":"Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?","created":"2022-03-16","cited_by_count":24,"area":null},{"id":"2406.09334","title":"ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models","created":"2024-06-13","cited_by_count":20,"area":null},{"id":"2106.03269","title":"Itihasa: A large-scale corpus for Sanskrit to English translation","created":"2021-06-06","cited_by_count":13,"area":null},{"id":"2502.12301","title":"SMOL: Professionally translated parallel data for 115 under-represented languages","created":"2025-02-17","cited_by_count":12,"area":null},{"id":"2305.08828","title":"PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India","created":"2023-05-15","cited_by_count":11,"area":null},{"id":"2301.08008","title":"Improving Machine Translation with Phrase Pair Injection and Corpus Filtering","created":"2023-01-19","cited_by_count":7,"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":"2306.01382","title":"Leveraging Auxiliary Domain Parallel Data in Intermediate Task Fine-tuning for Low-resource Translation","created":"2023-06-02","cited_by_count":5,"area":null},{"id":"2602.13139","title":"OpenLID-v3: Improving the Precision of Closely Related Language Identification -- An Experience Report","created":"2026-02-13","cited_by_count":5,"area":null},{"id":"2103.15877","title":"Unsupervised Machine Translation On Dravidian Languages","created":"2021-03-29","cited_by_count":4,"area":null},{"id":"2305.13641","title":"AxomiyaBERTa: A Phonologically-aware Transformer Model for Assamese","created":"2023-05-23","cited_by_count":4,"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":"2406.09559","title":"Decoding the Diversity: A Review of the Indic AI Research Landscape","created":"2024-06-13","cited_by_count":4,"area":null},{"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":"2601.20858","title":"When Flores Bloomz Wrong: Cross-Direction Contamination in Machine Translation Evaluation","created":"2026-01-28","cited_by_count":3,"area":null},{"id":"2201.05700","title":"Cost-Effective Training in Low-Resource Neural Machine Translation","created":"2022-01-14","cited_by_count":2,"area":null},{"id":"2306.03507","title":"\"A Little is Enough\": Few-Shot Quality Estimation based Corpus Filtering improves Machine Translation","created":"2023-06-06","cited_by_count":2,"area":null},{"id":"2412.19522","title":"Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation","created":"2024-12-27","cited_by_count":2,"area":null},{"id":"2304.13005","title":"Evaluating Inter-Bilingual Semantic Parsing for Indian Languages","created":"2023-04-25","cited_by_count":1,"area":null},{"id":"2411.05781","title":"Using Language Models to Disambiguate Lexical Choices in Translation","created":"2024-11-08","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":"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":"2605.12242","title":"Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2111.03813","title":"Analyzing Architectures for Neural Machine Translation Using Low Computational Resources","created":"2021-11-06","cited_by_count":0,"area":null},{"id":"2305.12371","title":"Machine Translation by Projecting Text into the Same Phonetic-Orthographic Space Using a Common Encoding","created":"2023-05-21","cited_by_count":0,"area":null},{"id":"2312.11312","title":"APE-then-QE: Correcting then Filtering Pseudo Parallel Corpora for MT Training Data Creation","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2411.00727","title":"SPRING Lab IITM's submission to Low Resource Indic Language Translation Shared Task","created":"2024-11-01","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},{"id":"2610.18818","title":"Back-Translation Still Matters: Leveraging Monolingual Data for Low-Resource Machine Translation with LLMs","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}