Papers with Bangla
BanglaSTEM: A Parallel Corpus and Term-Weighted Evaluation for Technical Bangla-English Translation (2026.acl-srw)
Copied to clipboard
| Challenge: | Large language models excel at technical problem solving in English but struggle when questions are posed in Bangla. |
| Approach: | They propose a dataset of 5,000 Bangla-English sentence pairs to align technical terms . they use OCR to extract matching passages from bilingual textbooks . |
| Outcome: | The proposed pipeline extracts matching passages from bilingual textbooks and uses them to align sentences and mark technical terms. |
BanSuite: A Unified Toolkit and Software Platform for Low-Resource NLP in Bangla (2026.eacl-demo)
Copied to clipboard
Md. Abu Sayed, Faisal Ahamed Khan, Jannatul Ferdous Tuli, Nabeel Mohammed, Mohammad Ruhul Amin, Mohammad Mamun Or Rashid
| Challenge: | Existing efforts to improve Bangla's NLP performance have focused on isolated tasks such as Part-of-Speech tagging and Named Entity Recognition (NER) but comprehensive, integrated systems for core NLP tasks such Shallow Parsing and Dependency Parser are largely absent. |
| Approach: | They propose to integrate a large-scale, manually annotated Bangla Treebank with high-quality pretrained models for POS tagging, NER, shallow parsing, and dependency parse. |
| Outcome: | The proposed system achieves strong in-domain baseline performance while maintaining high efficiency in resource usage. |
BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla (2023.findings-eacl)
Copied to clipboard
| Challenge: | 'BanglaNLG' is a comprehensive benchmark for evaluating natural language generation models in Bangla, a widely spoken yet low-resource language. |
| Approach: | They propose to aggregate six conditional text generation tasks under the BanglaNLG benchmark and introduce a new dataset on dialogue generation in the process. |
| Outcome: | The proposed model outperforms several multilingual models by 9% absolute gain and 32% relative gain on all of these tasks. |
An Empirical Study on the Characteristics of Bias upon Context Length Variation for Bangla (2024.findings-acl)
Copied to clipboard
| Challenge: | Language models exhibit various social biases due to widespread usage. |
| Approach: | They extend existing methods for measuring gender bias in Bangla by examining context length variation. |
| Outcome: | The proposed method relies on context length variation, highlighting the need for nuanced considerations in Bangla bias analysis. |
DiMLex-Bangla: A Lexicon of Bangla Discourse Connectives (2020.lrec-1)
Copied to clipboard
| Challenge: | Discourse connectives are widely believed to be the most explicit, prototypical and most reliable relational signals in discourse processing. |
| Approach: | They present a newly developed lexicon of Bangla discourse connectives . it contains 123 Bangla connective entries, which are primarily compiled from literature . |
| Outcome: | The lexicon contains 123 Bangla connective entries, which are compiled from the linguistic literature and translation of English discourse connectives. |
BanLemma: A Word Formation Dependent Rule and Dictionary Based Bangla Lemmatizer (2023.findings-emnlp)
Copied to clipboard
Sadia Afrin, Md. Shahad Mahmud Chowdhury, Md. Islam, Faisal Khan, Labib Chowdhury, Md. Mahtab, Nazifa Chowdhury, Massud Forkan, Neelima Kundu, Hakim Arif, Mohammad Mamun Or Rashid, Mohammad Amin, Nabeel Mohammed
| Challenge: | Lemmatization holds significance in both natural language processing (NLP) and linguistics due to the highly inflected nature and morphological richness of Bangla text. |
| Approach: | They propose linguistic rules for lemmatization and utilize a dictionary along with the rules to design a lemma specifically for Bangla. |
| Outcome: | The proposed system achieves 96.36% accuracy when tested against a manually annotated test dataset. |
Developing the Bangla RST Discourse Treebank (L18-1)
Copied to clipboard
| Challenge: | a corpus in Bangla is annotated for coherence relations between text segments representing propositions . the corpus is a valuable resource for conducting discourse studies for Bangla . |
| Approach: | They propose to build a Bangla-annotated corpus which includes 266 Bangla texts . they use Rhetorical Structure Theory as the theoretical framework to develop the corpus . |
| Outcome: | The proposed corpus contains 266 Bangla texts annotated for coherence relations . the research could be used for discourse studies and for developing NLP applications . |
BanglaByT5: Byte-Level Modelling for Bangla (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have achievedremarkable success across various natural lan-guage processing tasks. |
| Approach: | They propose a byte-level encoder-decoder model specifically tailored for Bangla. |
| Outcome: | The proposed model outperforms existing models in gen-erative and classification tasks and surpasses several multilingual and larger models. |
Deciphering Hate: Identifying Hateful Memes and Their Targets (2024.acl-long)
Copied to clipboard
| Challenge: | a growing body of research has focused on the negative aspects of memes in high-resource languages like Bengali . a new dataset for Bengali hateful memes is designed to detect their targeted entities . |
| Approach: | They propose a multimodal dataset that analyzes the modality of memes and compares them with other datasets. |
| Outcome: | The proposed dataset outperforms state-of-the-art datasets on Bengali hateful memes . the proposed dataset is generalizable on other low-resource hateful memes datasets compared with baselines based on the proposed model . |
On Evaluation of Bangla Word Analogies (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing word embeddings in Bangla struggle to perform well on low-resource data sets. |
| Approach: | They propose to use a benchmark dataset of Bangla word analogies to evaluate the quality of existing Bangla embeddings. |
| Outcome: | The proposed evaluation set includes 16,678 unique word analogies in Bangla and a translated and curated version of the original Mikolov dataset (10,594 samples) . |
BanglaTLit: A Benchmark Dataset for Back-Transliteration of Romanized Bangla (2024.findings-emnlp)
Copied to clipboard
| Challenge: | low-resource languages like Bangla are limited by the lack of datasets. |
| Approach: | They propose a large-scale transliteration dataset and a pre-training corpus on romanized Bangla. |
| Outcome: | The proposed datasets show that the proposed methods can enrich romanized Bangla. |
TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking (2025.findings-acl)
Copied to clipboard
Shahriar Kabir Nahin, Rabindra Nath Nandi, Sagor Sarker, Quazi Sarwar Muhtaseem, Md Kowsher, Apu Chandraw Shill, Md Ibrahim, Mehadi Hasan Menon, Tareq Al Muntasir, Firoj Alam
| Challenge: | Existing benchmarking datasets for Bangla LLMs are not available for all languages. |
| Approach: | They present TituLLMs, the first large pretrained Bangla LLMs, available in 1b and 3b parameter sizes. |
| Outcome: | The proposed model outperforms existing models in Bangla, but not always in the first place. |
Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis (2024.lrec-main)
Copied to clipboard
Md. Arid Hasan, Shudipta Das, Afiyat Anjum, Firoj Alam, Anika Anjum, Avijit Sarker, Sheak Rashed Haider Noori
| Challenge: | Recent performance of Large Language Models (LLMs) in low-resource languages is under-researched due to resource constraints. |
| Approach: | They present a manually annotated dataset encompassing 33,606 Bangla tweets and Facebook comments. |
| Outcome: | The proposed model outperforms other models even in zero and few-shot scenarios. |
LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target (2026.acl-long)
Copied to clipboard
| Challenge: | Existing work on social media platforms is limited in its ability to detect hate speech . a lack of reliable and scalable automated hate speech detection systems is a challenge for low-resource languages like Bangla. |
| Approach: | They propose to use a single-task, single-targeted, single language dataset to identify hate speech in Bangla. |
| Outcome: | The proposed dataset is the largest manually annotated Bangla hate-speech dataset to date. |
Paramanu: Compact and Competitive Monolingual Language Models for Low-Resource Morphologically Rich Indian Languages (2026.acl-long)
Copied to clipboard
| Challenge: | Multilingual large language models are expensive to pretrain and suffer from imbalances across languages and datasets. |
| Approach: | They propose a family of Indian language-only autoregressive language models trained on open-source language-specific data for the five most spoken Indian languages. |
| Outcome: | The proposed model outperforms most larger models up to 8B across all five languages. |
BanHADEX: Towards Explainable HAte Speech Detection in Bangla Using Human Annotated EXplanation (2026.acl-long)
Copied to clipboard
Faisal Hossain Raquib, Akm Moshiur Rahman Mazumder, Md Fahim, Md Tahmid Hasan Fuad, Md Farhan Ishmam, Faria Sultana, M Ashraful Amin, Amin Ahsan Ali, Akmmahbubur Rahman
| Challenge: | Existing studies in Bangla focus on hate classification while overlooking interpretability. |
| Approach: | They propose to create a dataset with human-annotated labels for banla that contains 19,203 YouTube comments spanning April 2024–June 2025. |
| Outcome: | The proposed dataset outperforms existing datasets on open and closed-source LLMs on interpretability and better understanding of hate speech in linguistically rich yet under-resourced languages. |