Beyond Clean Text: Evaluating Encoder and Decoder Robustness for Bangla Event Detection in Noisy Text

📅 2026-06-29
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the limited robustness of current event detection systems in real-world noisy scenarios for low-resource languages such as Bengali, despite their strong performance on clean text. The authors construct a Bengali news event benchmark dataset comprising 9,979 annotated sentences spanning clean text, ASR transcripts, and spelling-perturbed variants. They systematically evaluate the noise robustness of encoder-based models (e.g., BanglaBERT, XLM-R) and instruction-tuned decoder large language models (e.g., Llama 3, Gemma 2). The work reveals a fundamental difference in noise resilience between the two architectures: decoders exhibit greater robustness when trigger words are corrupted. By integrating annotation guidelines into instruction tuning and training on mixed clean-noisy data, the performance gap is substantially narrowed. Combining model scaling with multi-source joint training yields state-of-the-art results across diverse noise conditions.
📝 Abstract
Event detection (ED) systems are typically evaluated on clean, curated text, leaving their robustness to real-world noise largely unexplored, particularly for low-resource languages such as Bangla. We introduce a generalized Bangla news event ontology and a benchmark comprising 9,979 annotated sentences across 40 event subtypes, spanning clean news text, real-world Automatic Speech Recognition (ASR) transcripts, and orthographically corrupted text. We systematically evaluate fine-tuned encoder-only models (BanglaBERT and XLM-R) alongside instruction-tuned decoder-only large language models (Llama 3 and Gemma 3). Our results reveal a clear architectural trade-off: encoder models achieve higher performance on clean text but degrade substantially under noise, whereas decoder-only LLMs are markedly more robust, particularly when event triggers are corrupted. We further show that embedding annotation guidelines during instruction tuning establishes a higher performance baseline on noisy text but yields inconsistent reductions in performance degradation across noisy conditions. Finally, model scaling consistently improves the robustness of decoder-only LLMs, while combined training on clean and noisy data serves as an effective regularization strategy that disproportionately benefits encoder architectures, significantly narrowing the robustness gap.
Problem

Research questions and friction points this paper is trying to address.

event detection
noisy text
Bangla
robustness
low-resource languages
Innovation

Methods, ideas, or system contributions that make the work stand out.

event detection
noise robustness
encoder-decoder trade-off
low-resource languages
instruction tuning
🔎 Similar Papers
No similar papers found.
T
Tanvir Ahmed Sijan
Jahangirnagar University, Dhaka, Bangladesh
S
S. M Golam Rifat
Rajshahi University of Engineering & Technology, Rajshahi, Bangladesh
N
Nayeemul Islam
Bangladesh University of Engineering and Technology, Dhaka, Bangladesh
M
Md. Musfique Anwar
Jahangirnagar University, Dhaka, Bangladesh