Controllable Text Simplification

Abstract: Text simplification is a task of paraphrasing a given text in an easy-to-understand manner to assist a variety of people in language comprehension. To fully benefit from text simplification, consideration of individual differences in language ability is crucial. Over the past decade, much effort has been devoted to studying methods for text simplification that adapt expressions according to the target audience.

This presentation focuses on approaches to personalizing text simplification, specifically controlling readability and editing operations.

Bio: Tomoyuki Kajiwara received the B.S. and M.S. degrees in engineering from the Nagaoka University of Technology, Japan, in 2013 and 2015, respectively, and the Ph.D. degree in engineering from the Tokyo Metropolitan University, Japan, in 2018. From 2018 to 2020, he was a Specially-Appointed Assistant Professor with the Osaka University. He is currently an Assistant Professor with the Ehime University. His research interests include natural language processing, paraphrasing, and quality estimation.