India

We study sentence-level generative data augmentation for Bangla semantic classification across four public datasets and three pretrained model families (BanglaBERT, XLM-Indic, mBERT). We evaluate two widely used, reproducible techniques—paraphrasing (mT5-based) and round-trip backtranslation (Bn–En–Bn)—and analyze their impact under realistic class imbalance. Overall, augmentation often helps, but gains are tightly coupled to label quality: paraphrasing typically outperforms backtranslation and yields the most consistent improvements for the monolingual model, whereas multilingual encoders benefit less and can be more sensitive to noisy minority-class expansions. A key empirical observation is that the neutral class appears to be a major source of annotation noise, which degrades decision boundaries and can cap the benefits of augmentation even when positive/negative classes are clean and polarized. We provide practical guidance for Bangla sentiment pipelines: (i) use simple sentence-level augmentation to rebalance classes when labels are reliable; (ii) allocate additional curation and higher inter-annotator agreement targets to the neutral class. Our results indicate when augmentation helps and suggest that data quality—not model choice alone—can become the limiting factor.

IJCNLP-AACL 2025

A Comparative Analysis of Retrieval-Augmented Generation Techniques for Bengali Standard-to-Dialect Machine Translation Using LLMs

standard-to-dialect translation

bengali dialect translation

llms

hybrid retrieval

in-context learning

retrieval-augmented generation

low-resource machine translation

large language models

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

workshop paper

### Welcome to IJCNLP-AACL 2025! 
 It is a great honor to host this joint conference in Mumbai, India, from December 20 to 24, 2025. The joint conferences of IJCNLP and AACL are organized with alternating leadership in the Asia-Pacific region. The event is run by the Asian Federation of Natural Language Processing (AFNLP) in odd years, and by AACL in even years, while it is organized solely by ACL when the annual ACL meeting is held in the region. This year, the conference is primarily organized by AFNLP. 
*Kentaro Inui
MBZUAI, UAE
General Chair, IJCNLP-AACL 2025* 
Read full message and download the Conference Handbook [**here**](https://drive.google.com/file/d/1UTwxkAqSqI-GAoJC3wE1zZt5VP1Y8GX0/view?usp=sharing).

The 14th IJCNLP & 4th AACL will be held in Mumbai, India from December 20th to December 24th, 2025.

Aspect-Based Sentiment Analysis (ABSA) identifies sentiments toward specific aspects of an entity. While progress has been substantial for high-resource languages such as English, low-resource languages like Bangla remain underexplored due to limited annotated data and linguistic challenges. We propose Gen-mABSA-T5, a multilingual zero-shot generative framework for ABSA based on Flan-T5, incorporating prompt engineering and Natural Language Inference (NLI). Without task-specific training, Gen-mABSA-T5 achieves state-of-the-art zero-shot accuracy of 61.56% on the large Bangla corpus, 73.50% on SemEval Laptop, and 73.56% on SemEval Restaurant outperforming both English and Bangla task-specific models in zero-shot settings. It delivers reasonable performance against very large general-purpose models on both English and Bangla benchmarks. These results highlight the effectiveness of generative, zero-shot approaches for ABSA in low-resource and multilingual settings.

Generative Data Augmentation for Improving Semantic Classification

Online discourse in Bangla is rife with nuanced toxicity expressed through code-mixing, dialectal variation, and euphemism. Effective moderation thus requires fine-grained detection of hate type, target, and severity, rather than a binary label. To address this, we organized the Bangla Hate Speech Identification Shared Task at the BLP 2025 workshop, co-located with IJCNLP-AACL 2025, comprising three subtasks: (1A) hate-type detection, (1B) hate-target detection, and (1C) joint prediction of type, target, and severity in a multi-task setup. The subtasks attracted 161, 103, and 90 participants, with 36, 23, and 20 final submissions, respectively, while a total of 19 teams submitted system description papers. The submitted systems employed a wide range of approaches, ranging from classical machine learning to fine-tuned pretrained models and zero-/few-shot LLMs. We describe the task setup, datasets, and evaluation framework, and summarize participant systems. All datasets and evaluation scripts are publicly released.

Gen-mABSA-T5: A Multilingual Zero-Shot Generative Framework for Aspect-Based Sentiment Analysis

This paper presents an overview of the BLP 2025 shared task Code Generation in Bangla, organized with the BLP workshop co-located with AACL. The task evaluates Generative AI systems capable of generating executable Python code from natural language prompts written in Bangla. This is the first shared task to address Bangla code generation. It attracted 152 participants across 63 teams, yielding 488 submissions, with 15 system-description papers. Participating teams employed both proprietary and open-source LLMs, with prevalent strategies including prompt engineering, fine-tuning, and machine translation. The top Pass@1 reached 0.99 on the development phase and 0.95 on the test phase. In this report, we detail the task design, data, and evaluation protocol, and synthesize methodological trends observed across submissions. Notably, we observe that the high performance is not based on single models; rather, a pipeline of multiple AI tools and/or methods.

Code_Gen at BLP-2025 Task 1: Enhancing Bangla Hate Speech Detection with Transformers through Token-Aware Adversarial Contrastive Training and Layer-wise Learning Rate Decay

Detecting hate speech on social media is essential for safeguarding online communities, yet it remains challenging for low-resource languages like Bangla due to class imbalance and subjective annotations. We introduce a two-stage cascaded framework with $k$-fold ensembling to address the BLP Workshop 2025 Shared Task’s three subtasks: 1A (hate type classification), 1B (target identification), and 1C (joint classification of type, target, and severity). Our solution balances precision and recall, achieving micro-$F1$ scores of $0.7331$ on 1A, $0.7356$ on 1B, and $0.7392$ on 1C, ranking 4th on 1A and 1st on both 1B and 1C. It performs strongly on major classes, although underrepresented labels such as sexism and mild severity remain challenging. Our method makes the optimal use of limited data through $k$-fold ensembling and delivers overall balanced performance across majority and minority classes by mitigating class imbalance via cascaded layers.

CUET-NLP_Zenith at BLP-2025 Task 1: A Multi-Task Ensemble Approach for Detecting Hate Speech in Bengali YouTube Comments

Bangla social media contains several types of hate speech and slurs, but automatic detection is tough due to linguistic complexity, data imbalance and limited resources. We address this challenge in the BLP-2025 shared task by combining Token-Aware Adversarial Contrastive Training (TACT) with Layer-wise Learning Rate Decay (LLRD) to fine-tune transformer models like BanglaBERT, MuRIL, mE5-base and Twitter XLM-R. To capture the complementary strengths of each model, we aggregate the model outputs through logits ensembling and get a robust system for multiclass classification. On the official test set, our model achieved F1 scores of 0.7362 for hate type, 0.7335 for severity, and 0.7361 for target ranking, placing it 1st, 2nd, and 3rd, respectively. The findings indicate that adversarial fine-tuning with logits ensemble learning is a robust way to detect hate speech in resource-limited languages and provides valuable insights for multilingual and low-resource NLP research.

Overview of BLP-2025 Task 1: Bangla Hate Speech Identification

Hate speech on social media platforms, particularly in low-resource languages like Bengali, poses a significant challenge due to its nuanced nature and the need to understand its type, severity, and targeted group. To address this, the Bangla Multi-task Hate Speech Identification Shared Task at BLP 2025 adopts a multi-task learning framework that requires systems to classify Bangla YouTube comments across three subtasks simultaneously: type of hate, severity, and targeted group. To tackle these challenges, this work presents BanTriX, a transformer ensemble method that leverages BanglaBERT-I, XLM-R, and BanglaBERT-II. Evaluation results show that the BanTriX, optimized with cross-entropy loss, achieves the highest weighted micro F1-score of 73.78\% in Subtask 1C, securing our team 2nd place in the shared task.

PromptGuard at BLP-2025 Task 1: A Few-Shot Classification Framework Using Majority Voting and Keyword Similarity for Bengali Hate Speech Detection

This paper describes HateSense, our multi-task learning framework for the BLP 2025 shared task 1 on Bangla hate speech identification. The task requires not only detecting hate speech but also classifying its type, target, and severity. HateSense integrates binary and multi-label classifiers using both encoder- and decoder-based large language models (LLMs). We experimented with pre-trained encoder models (Bert based models), and decoder models like GPT-4.0, LLaMA 3.1 8B, and Gemma-2 9B. To address challenges such as class imbalance and the linguistic complexity of Bangla, we employed techniques like focal loss and odds ratio preference optimization (ORPO). Experimental results demonstrated that the pre-trained encoders (BanglaBert) achieved state-of-the-art performance. Among different prompting strategies, chain-of-thought (CoT) combined with few-shot prompting proved most effective. Following the HateSense framework, our system attained competitive micro-F1 scores: 0.741 (Task 1A), 0.724 (Task 1B), and 0.7233 (Task 1C). These findings affirm the effectiveness of transformer-based architectures for Bangla hate speech detection and suggest promising avenues for multi-task learning in low-resource languages.

Ecstasy at BLP-2025 Task 1: TF-IDF Informed Prompt Engineering with LoRA Fine-tuning for Bangla Hate Speech Detection

We present a hybrid approach for Bangla hate speech detection that combines linguistic analysis with neural fine tuning. Our method first identifies category specific keywords using TF-IDF analysis on 35,522 training samples. These keywords then inform prompt engineering for Llama 3.1 8B model fine tuned with LoRA adapters. We incorporate distinctive Bangla terms directly into classification prompts to guide the model understanding of hate speech patterns. Our system achieved top 5 rankings across all three BLP 2025 Task 1 subtasks including hate type classification, target identification, and multi task prediction. The approach proved particularly effective for culturally specific hate speech patterns unique to Bangla social media discourse.

Retriv at BLP-2025 Task 1: A Transformer Ensemble and Multi-Task Learning Approach for Bangla Hate Speech Identification

This paper addresses the problem of Bangla hate speech identification, a socially impactful yet linguistically challenging task. As part of the Bangla Multi-task Hate Speech Identification shared task at the BLP Workshop, IJCNLP-AACL 2025, we participated in all three subtasks: (1A) hate type classification, (1B) target group identification, and (1C) joint detection of type, severity, and target. For subtasks 1A and 1B, we employed a soft-voting ensemble of transformer models (BanglaBERT, MuRIL, IndicBERTv2). For subtask 1C, we trained three multitask variants and aggregated their predictions through a weighted voting ensemble. Our systems achieved micro-$f_{1}$ scores of 72.75\% (1A) and 72.69\% (1B), and a weighted micro-$f_{1}$ score of 72.62\% (1C). On the shared task leaderboard, these corresponded to 9th, 10th, and 7th positions, respectively. These results highlight the promise of transformer ensembles and weighted multitask frameworks for advancing Bangla hate speech detection in low-resource contexts. We made experimental scripts publicly available for the community.

BElite at BLP-2025 Task 1: Leveraging Ensemble for Multi Task Hate Speech Detection in Bangla

The widespread use of the internet has made sharing information on social media more convenient. At the same time, it provides a platform for individuals with malicious intent to easily spread hateful content. Since many users prefer to communicate in their native language, detecting hate speech in Bengali poses a significant challenge. This study aims to identify Bengali hate speech on social media platforms. A shared task on Bengali hate speech detection was organized by the Second Bangla Language Processing Workshop (BLP). To tackle this task, we implemented five traditional machine learning models (LR, SVM, RF, NB, XGB), three deep learning models (CNN, BiLSTM, CNN+BiLSTM), and three transformer-based models (Bangla-BERT, m-BERT, XLM-R). Among all models, a weighted ensemble of transformer models achieved the best performance.Our approach ranked \textbf{\textit{3\textsuperscript{rd}}} in Subtask 1A with a micro-\textit{F1} score of 0.734, \textbf{\textit{6\textsuperscript{th}}} in Subtask 1B with 0.7315, and, after post-competition experiments, \textbf{\textit{4\textsuperscript{th}}} in Subtask 1C with 0.735.

Downloads

Next from IJCNLP-AACL 2025

Generative Data Augmentation for Improving Semantic Classification

Similar lecture

Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval