Emotion cause extraction aims to identify the reasons behind a certainemotion expressed in text. It is a much more difficult task compared to emotionclassification. Inspired by recent advances in using deep memory networks forquestion answering (QA), we propose a new approach which considers emotioncause identification as a reading comprehension task in QA. Inspired byconvolutional neural networks, we propose a new mechanism to store relevantcontext in different memory slots to model context information. Our proposedapproach can extract both word level sequence features and lexical features.Performance evaluation shows that our method achieves the state-of-the-artperformance on a recently released emotion cause dataset, outperforming anumber of competitive baselines by at least 3.01% in F-measure.
展开▼
