Self-Supervised and Controlled Multi-Document Opinion Summarization
2020
We address the problem of unsupervised abstractive summarization of collections of user generated reviews through self-supervision and control. We propose a self-supervised setup that considers an individual document as a target summary for a set of similar documents. This setting makes training simpler than previous approaches by relying only on standard log-likelihood loss and mainstream models. We address the problem of hallucinations through the use of control codes, to steer the generation towards more coherent and relevant summaries.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
56
References
11
Citations
NaN
KQI