资源论文Unsupervised Neural Text Simplification

Unsupervised Neural Text Simplification

2019-09-24 | |  131 |   52 |   0

Abstract The paper presents a fifirst attempt towards unsupervised neural text simplifification that relies only on unlabeled text corpora. The core framework is composed of a shared encoder and a pair of attentional-decoders, crucially assisted by 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 public test data shows that the proposed model can perform text-simplifification at both lexical and syntactic levels, competitive to existing supervised methods. It also outperforms viable unsupervised baselines. Adding a few labeled pairs helps improve the performance further

上一篇:Towards Understanding Linear Word Analogies

下一篇:Variational Pretraining for Semi-supervised Text Classification

用户评价
全部评价

热门资源

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Rating-Boosted La...

    The performance of a recommendation system reli...

  • Hierarchical Task...

    We extend hierarchical task network planning wi...