Abstract : We present a novel approach to sentence simplification which departs from previous work in two main ways. First, it requires neither hand written rules nor a training corpus of aligned standard and simplified sentences. Second, sentence splitting operates on deep semantic structure. We show (i) that the unsupervised framework we propose is competitive with four state-of-the-art supervised systems and (ii) that our semantic based approach allows for a principled and effective handling of sentence splitting.
https://hal.inria.fr/hal-01623829
Contributor : Claire Gardent <>
Submitted on : Wednesday, October 25, 2017 - 4:58:17 PM Last modification on : Wednesday, January 6, 2021 - 6:48:04 AM Long-term archiving on: : Friday, January 26, 2018 - 2:52:05 PM
Shashi Narayan, Claire Gardent. Unsupervised Sentence Simplification Using Deep Semantics. The 9th International Natural Language Generation conference, Sep 2016, Edinburgh, United Kingdom. pp.111 - 120, ⟨10.18653/v1/W16-6620⟩. ⟨hal-01623829⟩