A Sequence-to-Structure Approach to Document-level Targeted Sentiment Analysis

Most previous studies on aspect-based sentiment analysis (ABSA) were carried out at the sentence level, while the research of documentlevel ABSA has not received enough attention. In this work, we focus on the document-level targeted sentiment analysis task, which aims to extract the opinion targets consisting of multilevel entities from a review document and predict their sentiments. We propose a Sequenceto-Structure (Seq2Struct) approach to address the task, which is able to explicitly model the hierarchical structure among multiple opinion targets in a document, and capture the longdistance dependencies among affiliated entities across sentences. In addition to the existing Seq2Seq approach, we further construct four strong baselines with different pretrained models. Experimental results on six domains show that our Seq2Struct approach outperforms all the baselines significantly. Aside from the performance advantage in outputting the multilevel target-sentiment pairs, our approach has another significant advantage -it can explicitly display the hierarchical structure of the opinion targets within a document. Our source code is publicly released at https://github.com/ NUSTM/Doc-TSA-Seq2Struct.