Corpus ID: 233025149

Convex Aggregation for Opinion Summarization

@article{Iso2021ConvexAF,
  title={Convex Aggregation for Opinion Summarization},
  author={Hayate Iso and Xiaolan Wang and Yoshihiko Suhara and Stefanos Angelidis and W. Tan},
  journal={ArXiv},
  year={2021},
  volume={abs/2104.01371}
}
Recent approaches for unsupervised opinion summarization have predominantly used the review reconstruction training paradigm. An encoder-decoder model is trained to reconstruct single reviews and learns a latent review encoding space. At summarization time, the unweighted average of latent review vectors is decoded into a summary. In this paper, we challenge the convention of simply averaging the latent vector set, and claim that this simplistic approach fails to consider variations in the… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 33 REFERENCES
Generating Sentences from a Continuous Space
Unsupervised Opinion Summarization as Copycat-Review Generation
MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization
LexRank: Graph-based Lexical Centrality as Salience in Text Summarization
Unsupervised Opinion Summarization with Noising and Denoising
Language Models are Unsupervised Multitask Learners
OpinionDigest: A Simple Framework for Opinion Summarization
Self-Supervised and Controlled Multi-Document Opinion Summarization
A Spectral Method for Unsupervised Multi-Document Summarization
...
1
2
3
4
...