Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance

Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance Masaru Isonuma1 Junichiro Mori1,2 Danushka Bollegala3 Ichiro Sakata1 1The University of Tokyo, Japan 2 RIKEN, Japan isonuma@ipr-ctr.t.u-tokyo.ac.jp3 University of Liverpool, United Kingdom mori@mi.u-tokyo.ac.jp danushka@liverpool.ac.uk isakata@ipr-ctr.t.u-tokyo.ac.jp Abstract This paper presents a novel unsupervised abstractive summarization method for opin- ionated texts. While the basic variational autoencoder-based models assume a unimodal Gaussian prior for the latent code of sentences, we alternate it with a recursive Gaussian mix- ture, where each mixture component corre- sponds to the latent code of a topic sentence and is mixed by a tree-structured topic distribu- tion. By decoding each Gaussian component, we generate sentences with tree-structured topic guidance, where the root sentence con- veys generic content, and the leaf sentences describe specific topics. Experimental results demonstrate that the generated topic sentences are appropriate as a summary of opinionated texts, which are more informative and cover more input contents than those generated by the recent unsupervised summarization model (Braˇzinskas et al., 2020). Furthermore, we demonstrate that the variance of latent Gauss- ians represents the granularity of sentences, an- alogous to Gaussian word embedding (Vilnis and McCallum, 2015). 1 Introduction Summarizing opinionated texts, such as product reviews and online posts on Web sites, has at- tracted considerable attention recently along with the development of e-commerce and social media. Although extractive approaches are widely used in document summarization (Erkan and Radev, 2004; Ganesan et al., 2010), they often fail to pro- vide an overview of the documents, particularly for opinionated texts (Carenini et al., 2013; Gerani et al., 2014). Abstractive summarization can over- come this challenge by paraphrasing and general- izing an entire document. Although supervised approaches have seen significant success with the development of neural architectures (See et al., 2017; Fabbri et al., 2019), they are limited to specific domains, e.g., news articles, where a large number of gold summaries are available. How- ever, the domain of opinionated texts is diverse; manually writing gold summaries is therefore costly. This lack in gold summaries has motivated prior work to develop unsupervised abstractive summa- rization of opinionated texts, for example, product reviews (Chu and Liu, 2019; Braˇzinskas et al., 2020; Amplayo and Lapata, 2020). While they generated consensus opinions by condensing in- put reviews, two key components were absent: topics and granularity (i.e., the level of detail). For instance, as shown in Figure 1, a gold summary of a restaurant review provides the overall impres- sion and details about certain topics, such as food, ambience, and service. Hence, a summary typi- cally comprises diverse topics, some of which are described in detail, whereas others are mentioned concisely. From this investigation, we capture the topic- tree structure of reviews and generate topic sen- tences, that is, sentences summarizing specified topics. In the topic-tree structure, the root sentence conveys generic content, and the leaf sentences mention specific topics. From the generated topic sentences, we extract sentences with appropriate topics and levels of granularity as a summary. Re- garding extractive summarization, capturing top- ics …

Content truncated to 500 words