Work

Unsupervised Sentence Simplification Using Deep Semantics

Year: 2016

Type: conference-paper

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.

Source: International Natural Language Generation Conference (INLG)

DOI: 10.18653/v1/w16-6620

Authors: Shashi Narayan, Claire Gardent

Institutions: University of Edinburgh, Centre National de la Recherche Scientifique, Laboratoire Lorrain de Recherche en Informatique et ses Applications

Language: English

Topic: Text Readability and Simplification

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Agence Nationale de la Recherche, Horizon 2020 Framework Programme

Awards: Generating Text from Semantic Web Data, G4127302550, G495187929