Unsupervised Neural Text Simplification.
2018
The paper presents a first attempt towards unsupervised neural text simplification that relies only on unlabeled text corpora. The core framework is composed of a shared encoder and a pair of attentional-decoders and gains knowledge of simplification through discrimination based-losses and denoising. The framework is trained using unlabeled text collected from en-Wikipedia dump. Our analysis (both quantitative and qualitative involving human evaluators) on a public test data shows that the proposed model can perform text-simplification at both lexical and syntactic levels, competitive to existing supervised methods. Addition of a few labelled pairs also improves the performance further. We open source our implementation for academic use.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
51
References
1
Citations
NaN
KQI