kk2018 at SemEval-2020 Task 9: Adversarial Training for Code-Mixing Sentiment Classification
Computation and Language
2020-09-10 v2
Abstract
Code switching is a linguistic phenomenon that may occur within a multilingual setting where speakers share more than one language. With the increasing communication between groups with different languages, this phenomenon is more and more popular. However, there are little research and data in this area, especially in code-mixing sentiment classification. In this work, the domain transfer learning from state-of-the-art uni-language model ERNIE is tested on the code-mixing dataset, and surprisingly, a strong baseline is achieved. Furthermore, the adversarial training with a multi-lingual model is used to achieve 1st place of SemEval-2020 Task 9 Hindi-English sentiment classification competition.
Cite
@article{arxiv.2009.03673,
title = {kk2018 at SemEval-2020 Task 9: Adversarial Training for Code-Mixing Sentiment Classification},
author = {Jiaxiang Liu and Xuyi Chen and Shikun Feng and Shuohuan Wang and Xuan Ouyang and Yu Sun and Zhengjie Huang and Weiyue Su},
journal= {arXiv preprint arXiv:2009.03673},
year = {2020}
}