TransSum: Translating Aspect and Sentiment Embeddings for Self-Supervised Opinion Summarization
Ke Wang, Xiaojun Wan
Abstract
In this paper, we propose a novel selfsupervised opinion summarization framework TransSum, which models opinion summaries as translations operating on the low-dimensional aspect and sentiment embedding spaces. Specifically, we propose two contrastive objectives to learn the crucial aspect and sentiment embeddings of reviews, by taking advantage of the intra-and inter-group invariances that have not been considered in previous studies. Furthermore, these embeddings can be used to reduce opinion redundancy and construct highly relevant reviews-summary pairs to train a supervised multi-input opinion summarization model. Experimental results on three different domains show that TransSum outperforms several strong baselines in generating informative, relevant and low-redundant summaries, unveiling the effectiveness of our approach.