Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
Open Access
- 8 September 2021
- journal article
- research article
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 9, 945-961
Abstract
This paper presents a novel unsupervised abstractive summarization method for opinionated 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 mixture, where each mixture component corresponds to the latent code of a topic sentence and is mixed by a tree-structured topic distribution. By decoding each Gaussian component, we generate sentences with tree-structured topic guidance, where the root sentence conveys 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 (Bražinskas et al., 2020). Furthermore, we demonstrate that the variance of latent Gaussians represents the granularity of sentences, analogous to Gaussian word embedding (Vilnis and McCallum, 2015).Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond2016
- Capturing Reliable Fine-Grained Sentiment Associations by Crowdsourcing and Best–Worst Scaling2016
- Image-Based Recommendations on Styles and Substitutes2015
- Effective Approaches to Attention-based Neural Machine Translation2015
- Nested Hierarchical Dirichlet ProcessesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Abstractive Summarization of Product Reviews Using Discourse Structure2014
- Modeling topic hierarchies with the recursive chinese restaurant process2012
- MULTI‐DOCUMENT SUMMARIZATION OF EVALUATIVE TEXTComputational Intelligence, 2012
- Modeling Local Coherence: An Entity-Based ApproachComputational Linguistics, 2008
- The use of MMR, diversity-based reranking for reordering documents and producing summaries1998