Japanese Lexical Complexity for Non-Native Readers: A New Dataset

Code

• github.com/naist-nlp/jalecon
  OfficialIn papernone★ 5
• github.com/gotutiyan/jalecon_baseline
  pytorch★ 0

Abstract

Lexical complexity prediction (LCP) is the task of predicting the complexity of words in a text on a continuous scale. It plays a vital role in simplifying or annotating complex words to assist readers. To study lexical complexity in Japanese, we construct the first Japanese LCP dataset. Our dataset provides separate complexity scores for Chinese/Korean annotators and others to address the readers' L1-specific needs. In the baseline experiment, we demonstrate the effectiveness of a BERT-based system for Japanese LCP.

Tasks

Reproductions