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}
}

• Stefanos Angelidis, Reinald Kim Amplayo, +2 authors Mirella Lapata
• Published 2020
• Computer Science
• ArXiv

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

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed