Don’t Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja

Abstract

We propose a simple yet effective approach for improving Korean word representations using additional linguistic annotation (i.e. Hanja). We employ cross-lingual transfer learning in training word representations by leveraging the fact that Hanja is closely related to Chinese. We evaluate the intrinsic quality of representations learned through our approach using the word analogy and similarity tests. In addition, we demonstrate their effectiveness on several downstream tasks, including a novel Korean news headline generation task. * Equal contribution. 1 Hanja and traditional Chinese characters are very similar but not completely identical. Some differences in strokes and language-exclusive characters exist.