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 . We propose a multi-task learning method to incorporate information from syntactic and semantic auxiliary tasks to create models that are more robust to these phenomena . Further we create two challenge datasets to evaluate model performance on negated and speculative samples . However, the results indicate that there is still much room for improvement in making our models more robustly to these linguistic phenomena such as negation, speculation scope detection, to create more robust models that can improve performance .

Author(s) :

Links : PDF - Abstract

Code :

Keywords : models - speculation - negation - phenomena - create -

Leave a Reply

Your email address will not be published. Required fields are marked *