HCMS在SemEval-2020任务9中的工作：一种用于代码混合文本情感分析的神经方法
计算与语言
2020-07-24 v1 信息检索
机器学习
神经与进化计算
摘要
涉及代码混合语言的问题往往受困于资源匮乏以及缺乏可用于复杂迁移学习的材料。在本文中，我们描述了针对Sentimix印地语-英语任务（涉及代码混合文本的情感分类）的提交方案，并以67.1%的F1分数证明，简单的卷积与注意力机制便可能产生合理的结果。
引用
@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}
}
备注
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