Abstract
Text classification is one of the primary NLP tasks where machine
learning (ML) is widely used. Even though the applied machine
learning models are similar, the classification task may address specific
challenges from language to language. The concept of model
explainability can provide an idea of how the models make decisions in
these situations. In this paper, The explainability of different text
classification models for Malayalam language, a morphologically rich
Dravidian language predominantly spoken in Kerala, was compared.
The experiments considered classification models from both traditional
ML and deep learning genres. The experiments were conducted on
three different datasets and explainability scores are formulated for
each of the selected models. The results of experiments showed that
deep learning models did very well with respect to performance
matrices whereas traditional machine learning models did well if not
better in the explainability part.
Authors
S. Akshay, Manu Madhavan
Indian Institute of Information Technology, Kottayam, India
Keywords
Model Explainability, Text Classification, Malayalam Language, Low Resource Languages, Natural Language Processing