OpinionDigest: A Simple Framework for Opinion Summarization

@article{Suhara2020OpinionDigestAS,
  title={OpinionDigest: A Simple Framework for Opinion Summarization},
  author={Yoshihiko Suhara and Xiaolan Wang and Stefanos Angelidis and W. Tan},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.01901}
}
We present OpinionDigest, an abstractive opinion summarization framework, which does not rely on gold-standard summaries for training. The framework uses an Aspect-based Sentiment Analysis model to extract opinion phrases from reviews, and trains a Transformer model to reconstruct the original reviews from these extractions. At summarization time, we merge extractions from multiple reviews and select the most popular ones. The selected opinions are used as input to the trained Transformer model… Expand
4 Citations
Few-Shot Learning for Opinion Summarization
  • PDF
Abstractive Opinion Tagging
  • PDF

References

SHOWING 1-10 OF 23 REFERENCES
Unsupervised Multi-Document Opinion Summarization as Copycat-Review Generation
  • 9
  • Highly Influential
  • PDF
Neural Summarization by Extracting Sentences and Words
  • 476
  • PDF
MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization
  • 58
  • Highly Influential
  • PDF
ExtremeReader: An interactive explorer for customizable and explainable review summarization
  • 2
  • PDF
Snippext: Semi-supervised Opinion Mining with Augmented Data
  • 8
  • PDF
Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision
  • 21
  • PDF
...
1
2
3
...