Iterative Edit-Based Unsupervised Sentence Simplification
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- June 2020
- DOI:
- 10.48550/arXiv.2006.09639
- arXiv:
- arXiv:2006.09639
- Bibcode:
- 2020arXiv200609639K
- Keywords:
-
- Computer Science - Computation and Language
- E-Print:
- The paper has been accepted to ACL 2020