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.
Cite
@article{arxiv.1908.09282,
title = {Don't Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja},
author = {Kang Min Yoo and Taeuk Kim and Sang-goo Lee},
journal= {arXiv preprint arXiv:1908.09282},
year = {2019}
}
Comments
7 pages (5 main pages, 2 appendix pages), 1 figure, accepted in EMNLP 2019 (Conference on Empirical Methods in Natural Language Processing)