Saved in:
Bibliographic Details
Main Authors: Baiju, Bajiyo, Manohar, Kavya, Pillai, Leena G, Sherly, Elizabeth
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.09957
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910743847239680
author Baiju, Bajiyo
Manohar, Kavya
Pillai, Leena G
Sherly, Elizabeth
author_facet Baiju, Bajiyo
Manohar, Kavya
Pillai, Leena G
Sherly, Elizabeth
contents In this work, we present the development of a reverse transliteration model to convert romanized Malayalam to native script using an encoder-decoder framework built with attention-based bidirectional Long Short Term Memory (Bi-LSTM) architecture. To train the model, we have used curated and combined collection of 4.3 million transliteration pairs derived from publicly available Indic language translitertion datasets, Dakshina and Aksharantar. We evaluated the model on two different test dataset provided by IndoNLP-2025-Shared-Task that contain, (1) General typing patterns and (2) Adhoc typing patterns, respectively. On the Test Set-1, we obtained a character error rate (CER) of 7.4%. However upon Test Set-2, with adhoc typing patterns, where most vowel indicators are missing, our model gave a CER of 22.7%.
format Preprint
id arxiv_https___arxiv_org_abs_2412_09957
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Romanized to Native Malayalam Script Transliteration Using an Encoder-Decoder Framework
Baiju, Bajiyo
Manohar, Kavya
Pillai, Leena G
Sherly, Elizabeth
Computation and Language
In this work, we present the development of a reverse transliteration model to convert romanized Malayalam to native script using an encoder-decoder framework built with attention-based bidirectional Long Short Term Memory (Bi-LSTM) architecture. To train the model, we have used curated and combined collection of 4.3 million transliteration pairs derived from publicly available Indic language translitertion datasets, Dakshina and Aksharantar. We evaluated the model on two different test dataset provided by IndoNLP-2025-Shared-Task that contain, (1) General typing patterns and (2) Adhoc typing patterns, respectively. On the Test Set-1, we obtained a character error rate (CER) of 7.4%. However upon Test Set-2, with adhoc typing patterns, where most vowel indicators are missing, our model gave a CER of 22.7%.
title Romanized to Native Malayalam Script Transliteration Using an Encoder-Decoder Framework
topic Computation and Language
url https://arxiv.org/abs/2412.09957