mlsanityData to 14 Oct 2026

BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla

arXiv 2205.11081 ↗First posted 23 May 2022cs.CLcited by 42

Not on the map. Why?

Abstract (arXiv)

This work presents BanglaNLG, a comprehensive benchmark for evaluating natural language generation (NLG) models in Bangla, a widely spoken yet low-resource language. We aggregate six challenging conditional text generation tasks under the BanglaNLG benchmark, introducing a new dataset on dialogue generation in the process. Furthermore, using a clean corpus of 27.5 GB of Bangla data, we pretrain BanglaT5, a sequence-to-sequence Transformer language model for Bangla. BanglaT5 achieves state-of-the-art performance in all of these tasks, outperforming several multilingual models by up to 9% absolute gain and 32% relative gain. We are making the new dialogue dataset and the BanglaT5 model publicly available at https://github.com/csebuetnlp/BanglaNLG in the hope of advancing future research on Bangla NLG.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Builds on 49 of its 67 references that are in the map. First posted on arXiv 23 May 2022.

Builds on

49 of 67 references.

References · 49

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  7. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  9. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  10. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  11. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  12. 2018Deep contextualized word representationscited by 2,290
37 more
  1. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  2. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  3. 2020GLU Variants Improve Transformercited by 1,804
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  5. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  6. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
  7. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  8. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  9. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  10. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  11. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  12. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  13. 2020XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalizationcited by 742
  14. 2018CoQA: A Conversational Question Answering Challengecited by 683
  15. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 652
  16. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 560
  17. 2019CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Datacited by 548
  18. 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 488
  19. 2021XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languagescited by 347
  20. 2020Multilingual Translation with Extensible Multilingual Pretraining and Finetuningcited by 287
  21. 2021The GEM Benchmark: Natural Language Generation, its Evaluation and Metricscited by 239
  22. 2020ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-trainingcited by 222
  23. 2019Leveraging Pre-trained Checkpoints for Sequence Generation Taskscited by 182
  24. 2017A Survey on Dialogue Systems: Recent Advances and New Frontierscited by 162
  25. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 145
  26. 2021BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Banglacited by 125
  27. 2017Controllable Abstractive Summarizationcited by 110
  28. 2020Pre-training via Paraphrasingcited by 92
  29. 2021What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpuscited by 80
  30. 2021IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generationcited by 57
  31. 2020Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translationcited by 53
  32. 2021DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation by Augmenting Pretrained Multilingual Encoderscited by 50
  33. 2020GLGE: A New General Language Generation Evaluation Benchmarkcited by 47
  34. 2021IndicBART: A Pre-trained Model for Indic Natural Language Generationcited by 39
  35. 2021ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generationcited by 31
  36. 2020Bengali Abstractive News Summarization(BANS): A Neural Attention Approachcited by 3
  37. 2021Pointer over Attention: An Improved Bangla Text Summarization Approach Using Hybrid Pointer Generator Networkcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 11; 2025: 16; 2026: 10.

42 papers.

Sort:

By area:

  1. 2023BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLPcited by 23
  2. 2023Dolphin: A Challenging and Diverse Benchmark for Arabic NLGcited by 22
  3. 2023Vashantor: A Large-scale Multilingual Benchmark Dataset for Automated Translation of Bangla Regional Dialects to Bangla Languagecited by 10
  4. 2025Where Are We? Evaluating LLM Performance on African Languagescited by 10
  5. 2025TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarkingcited by 9
  6. 2024Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMscited by 7
  7. 2025Performance Evaluation of Large Language Models in Bangla Consumer Health Query Summarizationcited by 6
  8. 2024Paramanu: Compact and Competitive Monolingual Language Models for Low-Resource Morphologically Rich Indian Languagescited by 5
  9. 2024Low-Resource Counterspeech Generation for Indic Languages: The Case of Bengali and Hindicited by 5
  10. 2024BanglaAutoKG: Automatic Bangla Knowledge Graph Construction with Semantic Neural Graph Filteringcited by 5
  11. 2024An Empirical Study of Gendered Stereotypes in Emotional Attributes for Bangla in Multilingual Large Language Modelscited by 5
  12. 2024Decoding the Diversity: A Review of the Indic AI Research Landscapecited by 4
30 more
  1. 2024An Empirical Study on the Characteristics of Bias upon Context Length Variation for Banglacited by 4
  2. 2023Intent Detection and Slot Filling for Home Assistants: Dataset and Analysis for Bangla and Sylheticited by 3
  3. 2023LowResource at BLP-2023 Task 2: Leveraging BanglaBert for Low Resource Sentiment Analysis of Bangla Languagecited by 3
  4. 2025Empowering Bengali Education with AI: Solving Bengali Math Word Problems through Transformer Modelscited by 3
  5. 2025Bridging Dialects: Translating Standard Bangla to Regional Variants Using Neural Modelscited by 3
  6. 2024Transcribing Bengali Text with Regional Dialects to IPA using District Guided Tokenscited by 2
  7. 2024BanglaDialecto: An End-to-End AI-Powered Regional Speech Standardizationcited by 2
  8. 2025Zero-Shot Multi-Label Classification of Bangla Documents: Large Decoders Vs. Classic Encoderscited by 2
  9. 2025BanglaByT5: Byte-Level Modelling for Banglacited by 2
  10. 2025CRaFT: An Explanation-Based Framework for Evaluating Cultural Reasoning in Multilingual Language Modelscited by 2
  11. 2026Reliability Gated Multi-Teacher Distillation for Low Resource Abstractive Summarizationcited by 2
  12. 2024Milestones in Bengali Sentiment Analysis leveraging Transformer-models: Fundamentals, Challenges and Future Directionscited by 1
  13. 2025BeliN: A Novel Corpus for Bengali Religious News Headline Generation using Contextual Feature Fusioncited by 1
  14. 2025Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?cited by 1
  15. 2025BanglaNirTox: A Large-scale Parallel Corpus for Explainable AI in Bengali Text Detoxificationcited by 1
  16. 2025BengaliFig: A Low-Resource Challenge for Figurative and Culturally Grounded Reasoning in Bengalicited by 1
  17. 2025Modeling Romanized Hindi and Bengali: Dataset Creation and Multilingual LLM Integrationcited by 1
  18. 2026KrishokChat: A Provenance-Traceable Multi-Task Bengali Agricultural Benchmark with Safety-Critical Chemical Advisorycited by 1
  19. 2024ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliterationcited by 0
  20. 2025Enhancing LLM Code Generation Capabilities through Test-Driven Development and Code Interpretercited by 0
  21. 2025MultiBanAbs: A Comprehensive Multi-Domain Bangla Abstractive Text Summarization Datasetcited by 0
  22. 2025Accelerating Bangla NLP Tasks with Automatic Mixed Precision: Resource-Efficient Training Preserving Model Efficacycited by 0
  23. 2026Understanding QA generation: Extracting Parametric and Contextual Knowledge with CQA for Low Resource Bangla Languagecited by 0
  24. 2026Surpassing Scale by Efficiency: A Compact 135M Parameter Foundational LLM Natively Adapted for the Bangla Languagecited by 0
  25. 2026When Does Knowledge Distillation Hurt? Reliability-Aware Distillation for Low-Resource Language Summarizationcited by 0
  26. 2026Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Formscited by 0
  27. 2026Unified Multi-Dialectal Neural Machine Translation for Bangla Using the Dwadash Benchmark Corpuscited by 0
  28. 2026LabourCrew: A Multi-Agent RAG Framework for Trustworthy Adversarial Deliberation and Statutory Reasoning over Labour Lawcited by 0
  29. 2026A Benchmark for Bangla Task-Oriented Dialogue Understandingcited by 0
  30. 2026Evaluating Large Language Models for Multilingual Abstractive Summarization: A Comprehensive Study of English and Bengalicited by 0