Viewpoint core information extraction based on sequence-to-sequence model

Pair-wise aspect and opinion terms extraction is a subtask of aspect-based sentiment analysis, which aims to extract the core information of opinions from comment sentences. Existing methods need to perform a large number of complex annotations on the data or generate a large number of negative samples, consume a lot of manpower and computationally expensive, in order to solve this problem, converting the task of pair-wise aspect and opinion terms extraction into a text generation task, an end-to-end generation framework based on sequence-to-sequence(Seq2Seq) model is given to generate pair-wise aspect and opinion terms. The encoder and decoder of the large pretrained model BART are adopted as the encoder and decoder of the Seq2Seq model in the proposed framework, combine the pointer mechanism to generate pair-wise aspect and opinion terms directly during decoding. The proposed model F1 score is 77.31% on the 15res dataset, which is a 3.74% improvement over the best baseline model. Experimental results show that the proposed model is better than other baseline models on the three data sets.