Restoring Rhythm: Punctuation Restoration Using Transformer Models for Bangla, A Low-Resource Language

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mamun, Md Obyedullahil, Mamun, Md Adyelullahil, Ahmad, Arif, Emu, Md. Imran Hossain
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909987143417856
author Mamun, Md Obyedullahil
Mamun, Md Adyelullahil
Ahmad, Arif
Emu, Md. Imran Hossain
author_facet Mamun, Md Obyedullahil
Mamun, Md Adyelullahil
Ahmad, Arif
Emu, Md. Imran Hossain
contents Punctuation restoration enhances the readability of text and is critical for post-processing tasks in Automatic Speech Recognition (ASR), especially for low-resource languages like Bangla. In this study, we explore the application of transformer-based models, specifically XLM-RoBERTa-large, to automatically restore punctuation in unpunctuated Bangla text. We focus on predicting four punctuation marks: period, comma, question mark, and exclamation mark across diverse text domains. To address the scarcity of annotated resources, we constructed a large, varied training corpus and applied data augmentation techniques. Our best-performing model, trained with an augmentation factor of alpha = 0.20%, achieves an accuracy of 97.1% on the News test set, 91.2% on the Reference set, and 90.2% on the ASR set. Results show strong generalization to reference and ASR transcripts, demonstrating the model's effectiveness in real-world, noisy scenarios. This work establishes a strong baseline for Bangla punctuation restoration and contributes publicly available datasets and code to support future research in low-resource NLP.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18448
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Restoring Rhythm: Punctuation Restoration Using Transformer Models for Bangla, A Low-Resource Language
Mamun, Md Obyedullahil
Mamun, Md Adyelullahil
Ahmad, Arif
Emu, Md. Imran Hossain
Computation and Language
Artificial Intelligence
Machine Learning
I.2; I.7
Punctuation restoration enhances the readability of text and is critical for post-processing tasks in Automatic Speech Recognition (ASR), especially for low-resource languages like Bangla. In this study, we explore the application of transformer-based models, specifically XLM-RoBERTa-large, to automatically restore punctuation in unpunctuated Bangla text. We focus on predicting four punctuation marks: period, comma, question mark, and exclamation mark across diverse text domains. To address the scarcity of annotated resources, we constructed a large, varied training corpus and applied data augmentation techniques. Our best-performing model, trained with an augmentation factor of alpha = 0.20%, achieves an accuracy of 97.1% on the News test set, 91.2% on the Reference set, and 90.2% on the ASR set. Results show strong generalization to reference and ASR transcripts, demonstrating the model's effectiveness in real-world, noisy scenarios. This work establishes a strong baseline for Bangla punctuation restoration and contributes publicly available datasets and code to support future research in low-resource NLP.
title Restoring Rhythm: Punctuation Restoration Using Transformer Models for Bangla, A Low-Resource Language
topic Computation and Language
Artificial Intelligence
Machine Learning
I.2; I.7
url https://arxiv.org/abs/2507.18448