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

• URL: http://arxiv.org/abs/2511.07304v1
• Date: Mon, 10 Nov 2025 17:07:09 GMT
• Title: Retriv at BLP-2025 Task 1: A Transformer Ensemble and Multi-Task Learning Approach for Bangla Hate Speech Identification
• Authors: Sourav Saha, K M Nafi Asib, Mohammed Moshiul Hoque,
• Abstract summary: This paper addresses the problem of Bangla hate speech identification, a socially impactful yet linguistically challenging task.<n>Our team "Retriv" participated in all three subtasks: (1A) hate type classification, (1B) target group identification, and (1C) joint detection of type, severity, and target.<n>Our systems achieved micro-f1 scores of 72.75% (1A) and 72.69% (1B), and a weighted micro-f1 score of 72.62% (1C)
• Score: 7.459430148112738
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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, our team "Retriv" 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-f1 scores of 72.75% (1A) and 72.69% (1B), and a weighted micro-f1 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.

Related papers

• SyntaxMind at BLP-2025 Task 1: Leveraging Attention Fusion of CNN and GRU for Hate Speech Detection [0.0]
  This paper describes our system used in the BLP-2025 Task 1: Hate Speech Detection.<n>Our approach integrates BanglaBERT embeddings with multiple parallel processing branches based on GRUs and CNNs, followed by attention and dense layers for final classification.<n>The proposed system demonstrated high competitiveness, obtaining 0.7345 micro F1-Score (2nd place) in Subtask 1A and 0.7317 micro F1-Score (5th place) in Subtask 1B.
  arXiv  Detail & Related papers  (2026-01-09T20:54:54Z)
• Gradient Masters at BLP-2025 Task 1: Advancing Low-Resource NLP for Bengali using Ensemble-Based Adversarial Training for Hate Speech Detection [1.2744523252873352]
  We present an ensemble-based fine-tuning strategy for addressing subtasks 1A (hate-type classification) and 1B (target group classification) in YouTube comments.<n>We propose a hybrid approach on a Bangla Language Model, which outperformed the baseline models and secured the 6th position in subtask 1A.
  arXiv  Detail & Related papers  (2025-11-23T07:29:09Z)
• GenAI Content Detection Task 1: English and Multilingual Machine-Generated Text Detection: AI vs. Human [71.42669028683741]
  We present a shared task on binary machine generated text detection conducted as a part of the GenAI workshop at COLING 2025.<n>The task consists of two subtasks: Monolingual (English) and Multilingual.<n>We provide a comprehensive overview of the data, a summary of the results, detailed descriptions of the participating systems, and an in-depth analysis of submissions.
  arXiv  Detail & Related papers  (2025-01-19T11:11:55Z)
• MasonPerplexity at Multimodal Hate Speech Event Detection 2024: Hate Speech and Target Detection Using Transformer Ensembles [6.2696956160552455]
  This paper presents the MasonPerplexity submission for the Shared Task on Multimodal Hate Speech Event Detection at CASE 2024 at EACL 2024. We use an XLM-roBERTa-large model for sub-task A and an ensemble approach combining XLM-roBERTa-base, BERTweet-large, and BERT-base for sub-task B.
  arXiv  Detail & Related papers  (2024-02-03T00:23:36Z)
• Mavericks at ArAIEval Shared Task: Towards a Safer Digital Space -- Transformer Ensemble Models Tackling Deception and Persuasion [0.0]
  We present our approaches for task 1-A and task 2-A of the shared task which focus on persuasion technique detection and disinformation detection respectively. The tasks use multigenre snippets of tweets and news articles for the given binary classification problem. We achieved a micro F1-score of 0.742 on task 1-A (8th rank on the leaderboard) and 0.901 on task 2-A (7th rank on the leaderboard) respectively.
  arXiv  Detail & Related papers  (2023-11-30T17:26:57Z)
• nlpBDpatriots at BLP-2023 Task 1: A Two-Step Classification for Violence Inciting Text Detection in Bangla [7.3481279783709805]
  In this paper, we discuss the nlpBDpatriots entry to the shared task on Violence Inciting Text Detection (VITD) The aim of this task is to identify and classify the violent threats, that provoke further unlawful violent acts. Our best-performing approach for the task is two-step classification using back translation and multilinguality which ranked 6th out of 27 teams with a macro F1 score of 0.74.
  arXiv  Detail & Related papers  (2023-11-25T13:47:34Z)
• Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE [93.98660272309974]
  This report briefly describes our submission Vega v1 on the General Language Understanding Evaluation leaderboard. GLUE is a collection of nine natural language understanding tasks, including question answering, linguistic acceptability, sentiment analysis, text similarity, paraphrase detection, and natural language inference. With our optimized pretraining and fine-tuning strategies, our 1.3 billion model sets new state-of-the-art on 4/9 tasks, achieving the best average score of 91.3.
  arXiv  Detail & Related papers  (2023-02-18T09:26:35Z)
• Overview of Abusive and Threatening Language Detection in Urdu at FIRE 2021 [50.591267188664666]
  We present two shared tasks of abusive and threatening language detection for the Urdu language. We present two manually annotated datasets containing tweets labelled as (i) Abusive and Non-Abusive, and (ii) Threatening and Non-Threatening. For both subtasks, m-Bert based transformer model showed the best performance.
  arXiv  Detail & Related papers  (2022-07-14T07:38:13Z)
• Modular Adaptive Policy Selection for Multi-Task Imitation Learning through Task Division [60.232542918414985]
  Multi-task learning often suffers from negative transfer, sharing information that should be task-specific. This is done by using proto-policies as modules to divide the tasks into simple sub-behaviours that can be shared. We also demonstrate its ability to autonomously divide the tasks into both shared and task-specific sub-behaviours.
  arXiv  Detail & Related papers  (2022-03-28T15:53:17Z)
• Fine-tuning of Pre-trained Transformers for Hate, Offensive, and Profane Content Detection in English and Marathi [0.0]
  This paper describes neural models developed for the Hate Speech and Offensive Content Identification in English and Indo-Aryan languages. For English subtasks, we investigate the impact of additional corpora for hate speech detection to fine-tune transformer models. For the Marathi tasks, we propose a system based on the Language-Agnostic BERT Sentence Embedding (LaBSE)
  arXiv  Detail & Related papers  (2021-10-25T07:11:02Z)
• Efficiently Identifying Task Groupings for Multi-Task Learning [55.80489920205404]
  Multi-task learning can leverage information learned by one task to benefit the training of other tasks. We suggest an approach to select which tasks should train together in multi-task learning models. Our method determines task groupings in a single training run by co-training all tasks together and quantifying the effect to which one task's gradient would affect another task's loss.
  arXiv  Detail & Related papers  (2021-09-10T02:01:43Z)
• HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units [81.53783563025084]
  We propose an offline clustering step to provide aligned target labels for a BERT-like prediction loss. A key ingredient of our approach is applying the prediction loss over the masked regions only. HuBERT shows up to 19% and 13% relative WER reduction on the more challenging dev-other and test-other evaluation subsets.
  arXiv  Detail & Related papers  (2021-06-14T14:14:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.