Code-mixing is an important and rapidly evolving mechanism of expression among multilingual populations on social media. Monolingual sentiment analysis techniques perform poorly on code-mixed text, partly because code-mixed text often involves resou…

In this paper, we have proposed an approach to transform supervised CNN classifier architecture into an unsupervised clustering model. We address “structuredness” and “diversity” of the dataset to migrate from supervised to unsupervised paradigm. Ou…

In this paper, we explored the usage of different emojis in different emotional contexts and the importance of different modalities towards emotion classification task. We have presented a multimodal emotion classification approach which makes use o…

In this paper, we present a novel straightforward method for estimating degrees of compositionality in noun phrases. The method is mixing hypernymy and distributional information of the noun phrases and their constituent words. To encode hypernymy i…