Late Fusion of Transformers for Sentiment Analysis of Code-Switched Data

Code-switching is a common phenomenon in multilingual communities and is often used on social media. However, sentiment analysis of code-switched data is a challenging yet less explored area of research. This paper aims to develop a sentiment analysis system for code-switched data. In this paper, we present a novel approach combining two transformers using logits of their output and feeding them to a neural network for classification. We show the efficacy of our approach using two benchmark datasets, viz., English-Hindi (En-Hi), and English-Spanish (En-Es) availed by Microsoft GLUECoS. Our approach results in an F 1 score of 73.66% for En-Es and 61.24% for En-Hi, significantly higher than the best model reported for the GLUECoS benchmark dataset.