期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2017
卷号：2017
页码：21-27
语种：English
出版社：ACL Anthology
摘要：Deep neural networks have achieved remarkable results across many language processing tasks, however they have been shown to be susceptible to overfitting and highly sensitive to noise, including adversarial attacks. In this work, we propose a linguistically-motivated approach for training robust models based on exposing the model to corrupted text examples at training time. We consider several flavours of linguistically plausible corruption, include lexical semantic and syntactic methods. Empirically, we evaluate our method with a convolutional neural model across a range of sentiment analysis datasets. Compared with a baseline and the dropout method, our method achieves better overall performance.
