Iterative Edit-Based Unsupervised Sentence Simplification

• DOI: 10.18653/v1/2020.acl-main.707
• Publication Date: 2020-07-29T14:14:43Z
• Authors: Dhruv Kumar; Lili Mou; Lukasz Golab; Olga Vechtomova
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; Computation and Language (cs.CL)

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.<br/>The paper has been accepted to ACL 2020<br/>