论文:Modelling Context and Syntactical Features for Aspect-based Sentiment Analysis地址:https://www.aclweb.org/anthology/2020.acl-main.293/ 这是ACL2020上的一篇长文,作者来自澳大利亚伍伦港大学。(感觉wollongong翻译成卧龙岗更带感) 在这篇文章中,作者没有使用一个端到端的模型,而是对属性词抽取(AE)和属性级情感分类(ASC)进行独立的研究。在AE任务中,作者结合了roberta、词法信息和句法信息;在ASC任务中,作者研究了如何在预训练语言中更好地结合句子和属性词。
1. Universal POS tags https://universaldependencies.org/u/pos/2. Omer Levy and Yoav Goldberg. 2014. Dependencybased word embeddings. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 302–308. https://www.aclweb.org/anthology/P14-2050/3. Biqing Zeng, Heng Yang, Ruyang Xu, Wu Zhou, and Xuli Han. 2019. Lcf: A local context focus mechanism for aspect-based sentiment classification. Applied Sciences, 9(16):3389. https://www.researchgate.net/publication/335238076_LCF_A_Local_Context_Focus_Mechanism_for_Aspect-Based_Sentiment_Classification