The majority of work in targeted sentiment analysis has concentrated on
finding better methods to improve the overall results. Within this paper we
show that these models are not robust to linguistic phenomena, specifically
negation and speculation. In this paper, we propose a multi-task learning
method to incorporate information from syntactic and semantic auxiliary tasks,
including negation and speculation scope detection, to create English-language
models that are more robust to these phenomena. Further we create two challenge
datasets to evaluate model performance on negated and speculative samples. We
find that multi-task models and transfer learning via language modelling can
improve performance on these challenge datasets, but the overall performances
indicate that there is still much room for improvement. We release both the
datasets and the source code at
this https URL

本文中，我们提出了一种多任务学习方法，将来自句法和语义辅助任务的信息（包括否定和推测范围检测）结合起来，创建了更具鲁棒性的英语语言模型，以处理定向情感分析中的语言现象，经实验证明，基于多任务和通过语言建模的迁移学习都能提高模型性能，但总体表现仍有改进的空间。我们在此链接上发布了数据集和源代码。