TCS Research at SemEval-2018 Task 1: Learning Robust Representations using Multi-Attention Architecture

Abstract

This paper presents system description of our submission to the SemEval-2018 task-1: Affect in tweets for the English language. We combine three different features generated using deep learning models and traditional methods in support vector machines to create a unified ensemble system. A robust representation of a tweet is learned using a multi-attention based architecture which uses a mixture of different pre-trained embeddings. In addition, analysis of different features is also presented. Our system ranked 2nd, 5th, and 7th in different subtasks among 75 teams.