English

Unsupervised Sentence Simplification Using Deep Semantics

Computation and Language 2016-09-08 v3

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.

Keywords

Cite

@article{arxiv.1507.08452,
  title  = {Unsupervised Sentence Simplification Using Deep Semantics},
  author = {Shashi Narayan and Claire Gardent},
  journal= {arXiv preprint arXiv:1507.08452},
  year   = {2016}
}

Comments

10 pages, INLG 2016

R2 v1 2026-06-22T10:22:17.510Z