Language Identification of Bengali-English Code-Mixed Data using Character & Phonetic based LSTM Models

Published in 15th International Conference on Computing and Information Technology, Bangkok, Thailand (accepted), 2018

Recommended citation: S. Mandal, S. D. Das and D. Das. Language Identification of Bengali-English Code-Mixed data using Character & Phonetic based LSTM Models . 15th International Conference on Computing and Information Technology, Bangkok, Thailand (accepted) (2018). https://arxiv.org/pdf/1803.03859.pdf

abstact
Language identification of social media text still remains a challenging task due to properties like code-mixing and inconsistent phonetic transliterations. In this paper, we present a supervised learning approach for language identification at the word level of low resource Bengali-English code-mixed data taken from social media. We employ two methods of word encoding, namely character based and root phone based to train our deep LSTM models. Utilizing these two models we created two ensemble models using stacking and threshold technique which gave 91.78% and 92.35% accuracies respectively on our testing data.

download paper here

@article{mandal2018language,
title={Language identification of bengali-english code-mixed data using character \& phonetic based lstm models},
author={Mandal, Soumil and Das, Sourya Dipta and Das, Dipankar},
journal={arXiv preprint arXiv:1803.03859},
year={2018}
}