{"total":53,"rows":[{"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":"2101.00204","title":"BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla","created":"2021-01-01","cited_by_count":125,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2205.11081","title":"BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla","created":"2022-05-23","cited_by_count":42,"area":null},{"id":"2210.05109","title":"BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset","created":"2022-10-11","cited_by_count":15,"area":null},{"id":"2203.03047","title":"Recent Advances in Neural Text Generation: A Task-Agnostic Survey","created":"2022-03-06","cited_by_count":14,"area":null},{"id":"2410.13153","title":"Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings","created":"2024-10-17","cited_by_count":14,"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":"2410.20817","title":"The Zeno's Paradox of `Low-Resource' Languages","created":"2024-10-28","cited_by_count":12,"area":null},{"id":"2212.03419","title":"JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset","created":"2022-12-07","cited_by_count":11,"area":null},{"id":"2307.05083","title":"Vacaspati: A Diverse Corpus of Bangla Literature","created":"2023-07-11","cited_by_count":10,"area":null},{"id":"2311.11142","title":"Vashantor: A Large-scale Multilingual Benchmark Dataset for Automated Translation of Bangla Regional Dialects to Bangla Language","created":"2023-11-18","cited_by_count":10,"area":null},{"id":"2305.17267","title":"CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translation","created":"2023-05-26","cited_by_count":9,"area":null},{"id":"2502.11187","title":"TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking","created":"2025-02-16","cited_by_count":9,"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":"2410.03576","title":"Table Question Answering for Low-resourced Indic Languages","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2210.10692","title":"Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages","created":"2022-10-19","cited_by_count":6,"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":"2407.06432","title":"An Empirical Study of Gendered Stereotypes in Emotional Attributes for Bangla in Multilingual Large Language Models","created":"2024-07-08","cited_by_count":5,"area":null},{"id":"2411.15999","title":"Multi-ToM: Evaluating Multilingual Theory of Mind Capabilities in Large Language Models","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2205.14462","title":"BAN-Cap: A Multi-Purpose English-Bangla Image Descriptions Dataset","created":"2022-05-28","cited_by_count":4,"area":null},{"id":"2307.07948","title":"Model Adaptation for ASR in low-resource Indian Languages","created":"2023-07-16","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":"2312.05671","title":"Hate Speech and Offensive Content Detection in Indo-Aryan Languages: A Battle of LSTM and Transformers","created":"2023-12-09","cited_by_count":4,"area":null},{"id":"2406.17375","title":"An Empirical Study on the Characteristics of Bias upon Context Length Variation for Bangla","created":"2024-06-25","cited_by_count":4,"area":null},{"id":"2502.11198","title":"ANCHOLIK-NER: A Benchmark Dataset for Bangla Regional Named Entity Recognition","created":"2025-02-16","cited_by_count":4,"area":null},{"id":"2304.02739","title":"Bengali Fake Review Detection using Semi-supervised Generative Adversarial Networks","created":"2023-04-05","cited_by_count":3,"area":null},{"id":"2303.09306","title":"BanglaCoNER: Towards Robust Bangla Complex Named Entity Recognition","created":"2023-03-16","cited_by_count":2,"area":null},{"id":"2304.04613","title":"On Evaluation of Bangla Word Analogies","created":"2023-04-10","cited_by_count":2,"area":null},{"id":"2307.06979","title":"Tackling Fake News in Bengali: Unraveling the Impact of Summarization vs. Augmentation on Pre-trained Language Models","created":"2023-07-13","cited_by_count":2,"area":null},{"id":"2601.01778","title":"BanglaIPA: Towards Robust Text-to-IPA Transcription with Contextual Rewriting in Bengali","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2310.14261","title":"RSM-NLP at BLP-2023 Task 2: Bangla Sentiment Analysis using Weighted and Majority Voted Fine-Tuned Transformers","created":"2023-10-22","cited_by_count":1,"area":null},{"id":"2311.06204","title":"BanglaBait: Semi-Supervised Adversarial Approach for Clickbait Detection on Bangla Clickbait Dataset","created":"2023-11-10","cited_by_count":1,"area":null},{"id":"2401.09446","title":"Explainable Multimodal Sentiment Analysis on Bengali Memes","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2409.02712","title":"A Data Selection Approach for Enhancing Low Resource Machine Translation Using Cross-Lingual Sentence Representations","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2411.15270","title":"BanglaEmbed: Efficient Sentence Embedding Models for a Low-Resource Language Using Cross-Lingual Distillation Techniques","created":"2024-11-22","cited_by_count":1,"area":null},{"id":"2501.01069","title":"BeliN: A Novel Corpus for Bengali Religious News Headline Generation using Contextual Feature Fusion","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2509.18081","title":"GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2510.07877","title":"Ready to Translate, Not to Represent? Bias and Performance Gaps in Multilingual LLMs Across Language Families and Domains","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2511.03498","title":"BanglaSTEM: A Parallel Corpus for Technical Domain Bangla-English Translation","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2106.06875","title":"Don't Rule Out Monolingual Speakers: A Method For Crowdsourcing Machine Translation Data","created":"2021-06-12","cited_by_count":0,"area":null},{"id":"2204.09964","title":"TEAM-Atreides at SemEval-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in Bangla","created":"2022-04-21","cited_by_count":0,"area":null},{"id":"2308.01987","title":"Bengali Fake Reviews: A Benchmark Dataset and Detection System","created":"2023-08-03","cited_by_count":0,"area":null},{"id":"2410.10219","title":"ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliteration","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2412.13924","title":"Language verY Rare for All","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2506.06813","title":"BTPD: A Multilingual Hand-curated Dataset of Bengali Transnational Political Discourse Across Online Communities","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2506.06816","title":"How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language","created":"2025-06-07","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":"2601.04534","title":"BanglaLorica: Design and Evaluation of a Robust Watermarking Algorithm for Large Language Models in Bangla Text Generation","created":"2026-01-08","cited_by_count":0,"area":"safety"},{"id":"2601.06041","title":"Lexical and Statistical Analysis of Bangla Newspaper and Literature: A Corpus-Driven Study on Diversity, Readability, and NLP Adaptation","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2602.22391","title":"Detecting Hate and Inflammatory Content in Bengali Memes: A New Multimodal Dataset and Co-Attention Framework","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2604.16665","title":"CBRS: Cognitive Blood Request System with Bilingual Dataset and Dual-Layer Filtering for Multi-Platform Social Streams","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2606.16383","title":"Surpassing Scale by Efficiency: A Compact 135M Parameter Foundational LLM Natively Adapted for the Bangla Language","created":"2026-06-15","cited_by_count":0,"area":null}],"next_cursor":null}