Controllable Sentence Simplification - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2019

Controllable Sentence Simplification

Abstract

Text simplification aims at making a text easier to read and understand by simplifying grammar and structure while keeping the underlying information identical. It is often considered an all-purpose generic task where the same simplification is suitable for all; however multiple audiences can benefit from simplified text in different ways. We adapt a discrete parametrization mechanism that provides explicit control on simplification systems based on Sequence-to-Sequence models. As a result, users can condition the simplifications returned by a model on parameters such as length, amount of paraphrasing, lexical complexity and syntactic complexity. We also show that carefully chosen values of these parameters allow out-of-the-box Sequence-to-Sequence models to outperform their standard counterparts on simplification benchmarks. Our model, which we call ACCESS (as shorthand for AudienCe-CEntric Sentence Simplification), increases the state of the art to 41.87 SARI on the WikiLarge test set, a +1.42 gain over previously reported scores.

Dates and versions

hal-02445874 , version 1 (20-01-2020)

Identifiers

Cite

Louis Martin, Benoît Sagot, Éric Villemonte de La Clergerie, Antoine Bordes. Controllable Sentence Simplification. 2019. ⟨hal-02445874⟩
88 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More