Controllable Text Simplification with Explicit Paraphrasing
This work addresses the need for more adaptable and varied text simplification systems for audiences requiring different readability levels, representing an incremental improvement over existing methods.
The paper tackled the problem of text simplification systems being limited to mostly deleting words and lacking adaptability to different audiences by proposing a hybrid approach combining linguistically-motivated rules with a neural paraphrasing model, resulting in a new state-of-the-art model that paraphrases more often and allows control over simplification operations.
Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that are trained end-to-end to perform all these operations simultaneously. However, such systems limit themselves to mostly deleting words and cannot easily adapt to the requirements of different target audiences. In this paper, we propose a novel hybrid approach that leverages linguistically-motivated rules for splitting and deletion, and couples them with a neural paraphrasing model to produce varied rewriting styles. We introduce a new data augmentation method to improve the paraphrasing capability of our model. Through automatic and manual evaluations, we show that our proposed model establishes a new state-of-the-art for the task, paraphrasing more often than the existing systems, and can control the degree of each simplification operation applied to the input texts.