Corpus ID: 216868126

Few-Shot Learning for Abstractive Multi-Document Opinion Summarization

@article{Brazinskas2020FewShotLF,
  title={Few-Shot Learning for Abstractive Multi-Document Opinion Summarization},
  author={Arthur Brazinskas and Mirella Lapata and Ivan Titov},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.14884}
}
Opinion summarization is an automatic creation of text reflecting subjective information expressed in multiple documents, such as user reviews of a product. The task is practically important and has attracted a lot of attention. However, due to a high cost of summary production, datasets large enough for training supervised models are lacking. Instead, the task has been traditionally approached with extractive methods that learn to select text fragments in an unsupervised or weakly-supervised… Expand
Identifying Helpful Sentences in Product Reviews

References

SHOWING 1-10 OF 32 REFERENCES
Unsupervised Opinion Summarization as Copycat-Review Generation
Unsupervised Multi-Document Opinion Summarization as Copycat-Review Generation
MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization
A Neural Attention Model for Abstractive Sentence Summarization
A Deep Reinforced Model for Abstractive Summarization
Get To The Point: Summarization with Pointer-Generator Networks
Generating Wikipedia by Summarizing Long Sequences
...
1
2
3
4
...