SOTAVerified

Iterative Edit-Based Unsupervised Sentence Simplification

2020-06-17ACL 2020Code Available1· sign in to hype

Dhruv Kumar, Lili Mou, Lukasz Golab, Olga Vechtomova

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We present a novel iterative, edit-based approach to unsupervised sentence simplification. Our model is guided by a scoring function involving fluency, simplicity, and meaning preservation. Then, we iteratively perform word and phrase-level edits on the complex sentence. Compared with previous approaches, our model does not require a parallel training set, but is more controllable and interpretable. Experiments on Newsela and WikiLarge datasets show that our approach is nearly as effective as state-of-the-art supervised approaches.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
NewselaEdit-Unsup-TSSARI30.44Unverified
TurkCorpusEdit-Unsup-TSSARI (EASSE>=0.2.1)37.85Unverified

Reproductions