Self-Supervised and Controlled Multi-Document Opinion Summarization
Résumé
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.
Domaines
Informatique et langage [cs.CL]Origine | Fichiers éditeurs autorisés sur une archive ouverte |
---|---|
Licence |