Iterative Edit-based Unsupervised Sentence Simplification

Dhruv Kumar, Lili Mou, Lukasz Golab, Olga Vechtomova . Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 2020 – 57 citations

[Paper]    
ACL Datasets Interpretability

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.

Similar Work