{"total":71,"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":"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":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116,"area":null},{"id":"2106.16138","title":"XLM-E: Cross-lingual Language Model Pre-training via ELECTRA","created":"2021-06-30","cited_by_count":72,"area":null},{"id":"2305.13820","title":"An Open Dataset and Model for Language Identification","created":"2023-05-23","cited_by_count":50,"area":null},{"id":"2104.08692","title":"MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs","created":"2021-04-18","cited_by_count":41,"area":null},{"id":"2106.06381","title":"Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment","created":"2021-06-11","cited_by_count":41,"area":null},{"id":"2310.16248","title":"GlotLID: Language Identification for Low-Resource Languages","created":"2023-10-24","cited_by_count":39,"area":null},{"id":"2203.12515","title":"A Survey on Cross-Lingual Summarization","created":"2022-03-23","cited_by_count":38,"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":"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":"2110.07871","title":"Socially Aware Bias Measurements for Hindi Language Representations","created":"2021-10-15","cited_by_count":29,"area":null},{"id":"2212.06742","title":"ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages","created":"2022-12-13","cited_by_count":29,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","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":"2109.10534","title":"Role of Language Relatedness in Multilingual Fine-tuning of Language Models: A Case Study in Indo-Aryan Languages","created":"2021-09-22","cited_by_count":24,"area":null},{"id":"2305.08487","title":"Taxi1500: A Multilingual Dataset for Text Classification in 1500 Languages","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2110.10472","title":"Multilingual Unsupervised Neural Machine Translation with Denoising Adapters","created":"2021-10-20","cited_by_count":22,"area":null},{"id":"2108.01887","title":"PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining","created":"2021-08-04","cited_by_count":21,"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":"2106.08680","title":"Evaluating Gender Bias in Hindi-English Machine Translation","created":"2021-06-16","cited_by_count":19,"area":null},{"id":"2110.02887","title":"Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings","created":"2021-10-06","cited_by_count":19,"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":"2105.15071","title":"Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data","created":"2021-05-31","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":"2409.17892","title":"EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2504.06011","title":"Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2107.11534","title":"MIPE: A Metric Independent Pipeline for Effective Code-Mixed NLG Evaluation","created":"2021-07-24","cited_by_count":7,"area":null},{"id":"2108.01861","title":"Quality Evaluation of the Low-Resource Synthetically Generated Code-Mixed Hinglish Text","created":"2021-08-04","cited_by_count":7,"area":null},{"id":"2205.11277","title":"When does Parameter-Efficient Transfer Learning Work for Machine Translation?","created":"2022-05-23","cited_by_count":7,"area":null},{"id":"2503.21670","title":"COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing","created":"2025-03-27","cited_by_count":7,"area":null},{"id":"2305.14263","title":"LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2104.08384","title":"\"Wikily\" Supervised Neural Translation Tailored to Cross-Lingual Tasks","created":"2021-04-16","cited_by_count":5,"area":null},{"id":"2106.00250","title":"ViTA: Visual-Linguistic Translation by Aligning Object Tags","created":"2021-06-01","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":"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":"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":"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":"2109.04443","title":"HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints","created":"2021-09-09","cited_by_count":3,"area":null},{"id":"2110.09393","title":"Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language","created":"2021-10-18","cited_by_count":3,"area":null},{"id":"2205.08605","title":"OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence Retrieval","created":"2022-05-17","cited_by_count":3,"area":null},{"id":"2205.09470","title":"Nebula-I: A General Framework for Collaboratively Training Deep Learning Models on Low-Bandwidth Cloud Clusters","created":"2022-05-19","cited_by_count":3,"area":null},{"id":"2211.07628","title":"Language Agnostic Code-Mixing Data Augmentation by Predicting Linguistic Patterns","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2412.20357","title":"HindiLLM: Large Language Model for Hindi","created":"2024-12-29","cited_by_count":3,"area":null},{"id":"2505.14553","title":"Pivot Language for Low-Resource Machine Translation","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2205.15544","title":"Refining Low-Resource Unsupervised Translation by Language Disentanglement of Multilingual Model","created":"2022-05-31","cited_by_count":2,"area":null},{"id":"2302.11766","title":"MUTANT: A Multi-sentential Code-mixed Hinglish Dataset","created":"2023-02-23","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":"2308.16075","title":"Impact of Visual Context on Noisy Multimodal NMT: An Empirical Study for English to Indian Languages","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2310.18862","title":"Counterfactually Probing Language Identity in Multilingual Models","created":"2023-10-29","cited_by_count":2,"area":null},{"id":"2204.00871","title":"Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding","created":"2022-04-02","cited_by_count":1,"area":null},{"id":"2208.00463","title":"Mismatching-Aware Unsupervised Translation Quality Estimation For Low-Resource Languages","created":"2022-07-31","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":"2305.03207","title":"Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages","created":"2023-05-04","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":"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":"2511.22769","title":"Modeling Romanized Hindi and Bengali: Dataset Creation and Multilingual LLM Integration","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2101.06949","title":"HinFlair: pre-trained contextual string embeddings for pos tagging and text classification in the Hindi language","created":"2021-01-18","cited_by_count":0,"area":null},{"id":"2104.00106","title":"Zero-Shot Language Transfer vs Iterative Back Translation for Unsupervised Machine Translation","created":"2021-03-31","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":"2301.00688","title":"Active Learning for Neural Machine Translation","created":"2022-12-30","cited_by_count":0,"area":null},{"id":"2304.03169","title":"Selective Data Augmentation for Robust Speech Translation","created":"2023-03-22","cited_by_count":0,"area":null},{"id":"2309.13222","title":"Hindi to English: Transformer-Based Neural Machine Translation","created":"2023-09-23","cited_by_count":0,"area":null},{"id":"2405.01858","title":"SUKHSANDESH: An Avatar Therapeutic Question Answering Platform for Sexual Education in Rural India","created":"2024-05-03","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":"2603.18911","title":"Progressive Training for Explainable Citation-Grounded Dialogue: Reducing Hallucination to Zero in English-Hindi LLMs","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.01425","title":"The power of context: Random Forest classification of near synonyms. A case study in Modern Hindi","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.01601","title":"Contrast Matters: Understanding Robustness of In-Context Fine-Tuning to Target-Context Relatedness","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.19066","title":"The Annotation Scarcity Paradox in Low-Resource NLP Evaluation: A Decade of Acceleration and Emerging Constraints","created":"2026-05-18","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}