A Constrained Sequence-to-Sequence Neural Model for Sentence Simplification
This addresses sentence simplification for people with language impairments, but appears incremental as it builds on existing word-level and sentence-level methods.
The authors tackled sentence simplification by proposing a two-step framework combining word-level and sentence-level approaches, which achieved better performance than various baselines on Wikipedia and Simple Wikipedia datasets.
Sentence simplification reduces semantic complexity to benefit people with language impairments. Previous simplification studies on the sentence level and word level have achieved promising results but also meet great challenges. For sentence-level studies, sentences after simplification are fluent but sometimes are not really simplified. For word-level studies, words are simplified but also have potential grammar errors due to different usages of words before and after simplification. In this paper, we propose a two-step simplification framework by combining both the word-level and the sentence-level simplifications, making use of their corresponding advantages. Based on the two-step framework, we implement a novel constrained neural generation model to simplify sentences given simplified words. The final results on Wikipedia and Simple Wikipedia aligned datasets indicate that our method yields better performance than various baselines.