Unsupervised Opinion Summarization with Noising and Denoising

Abstract

The recent success of deep learning techniques for abstractive summarization is predicated on the availability of largescale datasets. When summarizing reviews (e.g., for products or movies), such training data is neither available nor can be easily sourced, motivating the development of methods which rely on synthetic datasets for supervised training. We show that explicitly incorporating content planning in a summarization model not only yields output of higher quality, but also allows the creation of synthetic datasets which are more natural, resembling real world document-summary pairs. Our content plans take the form of aspect and sentiment distributions which we induce from data without access to expensive annotations. Synthetic datasets are created by sampling pseudo-reviews from a Dirichlet distribution parametrized by our content planner, while our model generates summaries based on input reviews and induced content plans. Experimental results on three domains show that our approach outperforms competitive models in generating informative, coherent, and fluent summaries that capture opinion consensus.

Better Highlighting: Creating Sub-Sentence Summary Highlights

“…We aim to produce summary highlights in this paper, which will be overlaid on source documents to allow summaries to be interpreted in context. Generation of summary highlights is of crucial importance to tasks such as producing informative snippets from search outputs (Kaisser et al, 2008), summarizing viewpoints in opinionated text (Paul et al, 2010;Amplayo and Lapata, 2020), and annotating website privacy policies to assist users in answering important questions (Sadeh et al, 2013). Determining the most appropriate textual unit for highlighting, however, has been an understudied problem.…”

Extractive Opinion Summarization in Quantized Transformer Spaces

“…Early work (Hu and Liu, 2004) focused on numerically aggregating customer satisfaction across different aspects of the entity under consideration (e.g., the quality of a camera, its size, clarity). More recently, the success of neural summarizers in the Wikipedia and news domains (Cheng and Lapata, 2016;See et al, 2017;Narayan et al, 2018;Liu et al, 2018;Perez-Beltrachini etal., 2019) has spurred interest in opinion summarization; the aggregation, in textual form, of opinions expressed in a set of reviews (Angelidis and Lapata, 2018;Huy Tien et al, 2019;Tian et al, 2019;Coavoux et al, 2019;Chu and Liu, 2019;Isonuma et al, 2019;Bražinskas et al, 2020;Amplayo and Lapata, 2020;.…”

Self-Supervised Multimodal Opinion Summarization

“…Accordingly, studies used an unsupervised approach for opinion summarization (Ku et al, 2006;Paul et al, 2010;Carenini et al, 2013;Ganesan et al, 2010;Gerani et al, 2014). Recent studies Amplayo and Lapata, 2020;Elsahar et al, 2021) used a self-supervised learning framework that creates a synthetic pair of source reviews and a pseudo summary by sampling a review text from a training corpus and considering it as a pseudo summary, as in Figure 1a.…”