Problems involving code-mixed language are often plagued by a lack of resources and an absence of materials to perform sophisticated transfer learning with. In this paper we describe our submission to the Sentimix Hindi-English task involving sentiment classification of code-mixed texts, and with an F1 score of 67.1%, we demonstrate that simple convolution and attention may well produce reasonable results.
@article{arxiv.2007.12076,
title = {HCMS at SemEval-2020 Task 9: A Neural Approach to Sentiment Analysis for Code-Mixed Texts},
author = {Aditya Srivastava and V. Harsha Vardhan},
journal= {arXiv preprint arXiv:2007.12076},
year = {2020}
}
Comments
6 pages, 2 figures, 4 tables, math equations, to be published in the proceedings of the 14th International Workshop on Semantic Evaluation (SemEval) 2020, Association for Computational Linguistics (ACL). Code for the paper is available at https://github.com/IamAdiSri/hcms-semeval20 . Data and task description is available at https://competitions.codalab.org/competitions/20654