Robust Training under Linguistic Adversity

Yitong Li, Trevor Cohn, Timothy Baldwin
2017 Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers  
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.
more » ... actic 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.
doi:10.18653/v1/e17-2004 dblp:conf/eacl/BaldwinCL17 fatcat:osdzobqrcbdfxnv6dzip7b36wi