Unsupervised Sentence Simplification Using Deep Semantics

WS 2016  ·  Shashi Narayan, Claire Gardent ·

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.

PDF Abstract WS 2016 PDF WS 2016 Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text Simplification PWKP / WikiSmall UNSUP BLEU 38.47 # 2

Methods


No methods listed for this paper. Add relevant methods here