2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys)
Download PDF

Abstract

Current English lexical simplification (LS) methods adopt one simplification scheme for all users, regardless of individual users' language proficiency. To solve the problem, we propose a personalized English LS method for Chinese based on their English certification. Specifically, our method only simplifies these words that need to be simplified and utilizes both pertained language modeling BERT and Thesaurus to generate the best substitutes. To our knowledge, this is the first work that focuses on personalized English LS for Chinese. Experimental results show that our method obtains the most suitable simplification compared with the baselines.
Like what you’re reading?
Already a member?
Get this article FREE with a new membership!

Related Articles