Publication Type : Conference Paper
Publisher : Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages
Source : Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages, Association for Computational Linguistics, Kyiv (2021)
Url : https://aclanthology.org/2021.dravidianlangtech-1.34
Campus : Coimbatore
School : School of Artificial Intelligence, School of Artificial Intelligence - Coimbatore, School of Engineering
Center : Computational Engineering and Networking
Department : Center for Computational Engineering and Networking (CEN), Electronics and Communication
Year : 2021
Abstract : This paper describes the submission of the team Amrita_CEN_NLP to the shared task on Offensive Language Identification in Dravidian Languages at EACL 2021. We implemented three deep neural network architectures such as a hybrid network with a Convolutional layer, a Bidirectional Long Short-Term Memory network (Bi-LSTM) layer and a hidden layer, a network containing a Bi-LSTM and another with a Bidirectional Recurrent Neural Network (Bi-RNN). In addition to that, we incorporated a cost-sensitive learning approach to deal with the problem of class imbalance in the training data. Among the three models, the hybrid network exhibited better training performance, and we submitted the predictions based on the same.
Cite this Research Publication : Sreelakshmi, K., Premjith, B., Soman, K.P., Amrita CEN NLP@DravidianLangTech-EACL2021: "Deep Learning-based Offensive Language Identification in Malayalam, Tamil and Kannada", (2021) Proceedings of the 1st Workshop on Speech and Language Technologies for Dravidian Languages, DravidianLangTech 2021 at 16th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2021, pp. 249-254.