Self-Supervised and Controlled Multi-Document Opinion Summarization
Hady Elsahar, Maximin Coavoux, Jos Rozen, Matthias Gallé
Generation and Summarization Long paper Paper
You can open the pre-recorded video in separate windows.
Abstract:
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.
NOTE: Video may display a random order of authors.
Correct author list is at the top of this page.