{"total":41,"rows":[{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2309.07445","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","created":"2023-09-14","cited_by_count":152,"area":null},{"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":"2209.12226","title":"Re-contextualizing Fairness in NLP: The Case of India","created":"2022-09-25","cited_by_count":55,"area":null},{"id":"2311.05845","title":"Tamil-Llama: A New Tamil Language Model Based on Llama 2","created":"2023-11-10","cited_by_count":32,"area":null},{"id":"2304.09972","title":"MasakhaNEWS: News Topic Classification for African languages","created":"2023-04-19","cited_by_count":31,"area":null},{"id":"2104.07505","title":"Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models","created":"2021-04-15","cited_by_count":15,"area":null},{"id":"2304.11434","title":"L3Cube-IndicSBERT: A simple approach for learning cross-lingual sentence representations using multilingual BERT","created":"2023-04-22","cited_by_count":15,"area":null},{"id":"2107.03844","title":"A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models","created":"2021-07-08","cited_by_count":13,"area":null},{"id":"2504.16977","title":"Tokenization Matters: Improving Zero-Shot NER for Indic Languages","created":"2025-04-23","cited_by_count":12,"area":null},{"id":"2211.11187","title":"L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi","created":"2022-11-21","cited_by_count":10,"area":null},{"id":"2508.08424","title":"Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment","created":"2025-08-11","cited_by_count":9,"area":null},{"id":"2401.02254","title":"L3Cube-IndicNews: News-based Short Text and Long Document Classification Datasets in Indic Languages","created":"2024-01-04","cited_by_count":8,"area":null},{"id":"2101.04144","title":"Evaluation of Deep Learning Models for Hostility Detection in Hindi Text","created":"2021-01-11","cited_by_count":7,"area":null},{"id":"2205.05901","title":"Mitigating Gender Stereotypes in Hindi and Marathi","created":"2022-05-12","cited_by_count":6,"area":null},{"id":"2406.08726","title":"Standard Language Ideology in AI-Generated Language","created":"2024-06-13","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":"2502.18148","title":"NusaAksara: A Multimodal and Multilingual Benchmark for Preserving Indonesian Indigenous Scripts","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2505.23714","title":"SenWiCh: Sense-Annotation of Low-Resource Languages for WiC using Hybrid Methods","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2106.04995","title":"Crosslingual Embeddings are Essential in UNMT for Distant Languages: An English to IndoAryan Case Study","created":"2021-06-09","cited_by_count":3,"area":null},{"id":"2112.08087","title":"Cognition-aware Cognate Detection","created":"2021-12-15","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":"2201.05700","title":"Cost-Effective Training in Low-Resource Neural Machine Translation","created":"2022-01-14","cited_by_count":2,"area":null},{"id":"2407.12481","title":"Krutrim LLM: A Novel Tokenization Strategy for Multilingual Indic Languages with Petabyte-Scale Data Processing","created":"2024-07-17","cited_by_count":2,"area":null},{"id":"2508.17444","title":"MahaParaphrase: A Marathi Paraphrase Detection Corpus and BERT-based Models","created":"2025-08-24","cited_by_count":1,"area":null},{"id":"2512.01852","title":"BHRAM-IL: A Benchmark for Hallucination Recognition and Assessment in Multiple Indian Languages","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2603.14053","title":"NepTam: A Nepali-Tamang Parallel Corpus and Baseline Machine Translation Experiments","created":"2026-03-14","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":"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":"2204.02155","title":"Detecting Anchors' Opinion in Hinghlish News Delivery","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2207.03256","title":"Part-of-Speech Tagging of Odia Language Using statistical and Deep Learning-Based Approaches","created":"2022-07-07","cited_by_count":0,"area":null},{"id":"2309.13561","title":"Cordyceps@LT-EDI: Patching Language-Specific Homophobia/Transphobia Classifiers with a Multilingual Understanding","created":"2023-09-24","cited_by_count":0,"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":"2505.11177","title":"Low-Resource Language Processing: An OCR-Driven Summarization and Translation Pipeline","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2603.23521","title":"Chitrakshara: A Large Multilingual Multimodal Dataset for Indian languages","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.29221","title":"SiPaKosa: A Comprehensive Corpus of Canonical and Classical Buddhist Texts in Sinhala and Pali","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2607.23319","title":"BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2608.05104","title":"BnBERT-iPET: Sparse Few-Shot Language Modeling for Bengali via Lottery Ticket Pruning","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.29919","title":"IndicDetect: Evaluating Cross-Lingual LLM-Generated Text Detection for Hindi, Telugu, and Tamil","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.04755","title":"Vectorizing Classical Tamil: Representation Learning for Verse-Commentary Pairs","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.13721","title":"Scaling Hindi Quantum Natural Language Processing through Automatic Pregroup Supertagging","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}