Joint Opinion Relation Detection Using One-Class Deep Neural Network

Detecting opinion relation is a crucial step for fine-gained opinion summarization. A valid opinion relation has three requirements: a correct opinion word, a correct opinion target and the linking relation between them. Previous works prone to only verifying two of these requirements for opinion extraction, while leave the other requirement unverified. This could inevitably introduce noise terms. To tackle this problem, this paper proposes a joint approach, where all three requirements are simultaneously verified by a deep neural network in a classification scenario. Some seeds are provided as positive labeled data for the classifier. However, negative labeled data are hard to acquire for this task. We consequently introduce one-class classification problem and develop a One-Class Deep Neural Network. Experimental results show that the proposed joint approach significantly outperforms state-of-the-art weakly supervised methods.