English

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

Computation and Language 2021-06-16 v1 Artificial Intelligence Machine Learning

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 (Bra\v{z}inskas 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

Cite

@article{arxiv.2106.08007,
  title  = {Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance},
  author = {Masaru Isonuma and Junichiro Mori and Danushka Bollegala and Ichiro Sakata},
  journal= {arXiv preprint arXiv:2106.08007},
  year   = {2021}
}

Comments

accepted to TACL, pre-MIT Press publication version

R2 v1 2026-06-24T03:12:51.052Z