Corpus ID: 227745131

Extractive Opinion Summarization in Quantized Transformer Spaces

@article{Angelidis2020ExtractiveOS,
  title={Extractive Opinion Summarization in Quantized Transformer Spaces},
  author={Stefanos Angelidis and Reinald Kim Amplayo and Yoshihiko Suhara and Xiaolan Wang and Mirella Lapata},
  journal={ArXiv},
  year={2020},
  volume={abs/2012.04443}
}
We present the Quantized Transformer (QT), an unsupervised system for extractive opinion summarization. QT is inspired by Vector-Quantized Variational Autoencoders, which we repurpose for popularity-driven summarization. It uses a clustering interpretation of the quantized space and a novel extraction algorithm to discover popular opinions among hundreds of reviews, a significant step towards opinion summarization of practical scope. In addition, QT enables controllable summarization without… Expand

References

SHOWING 1-10 OF 46 REFERENCES
OpinionDigest: A Simple Framework for Opinion Summarization
  • 4
  • PDF
Unsupervised Aspect-Based Multi-Document Abstractive Summarization
  • 7
  • Highly Influential
  • PDF
Unsupervised Opinion Summarization with Noising and Denoising
  • 13
  • PDF
MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization
  • 58
  • Highly Influential
  • PDF
Informative and Controllable Opinion Summarization
  • 11
  • PDF
Opinions Summarization: Aspect Similarity Recognition Relaxes The Constraint of Predefined Aspects
  • 2
  • PDF
Unsupervised Opinion Summarization as Copycat-Review Generation
  • 16
  • Highly Influential
  • PDF
Ranking Sentences for Extractive Summarization with Reinforcement Learning
  • 253
  • PDF
Aspect and Opinion Aware Abstractive Review Summarization with Reinforced Hard Typed Decoder
  • 5
  • Highly Influential
  • PDF
Neural Summarization by Extracting Sentences and Words
  • 476
  • PDF
...
1
2
3
4
5
...