Don't Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja
This addresses the challenge of enhancing natural language processing for Korean, but it is incremental as it builds on existing cross-lingual methods with a specific linguistic adaptation.
The paper tackled the problem of improving Korean word representations by incorporating Hanja, a linguistic annotation related to Chinese, using cross-lingual transfer learning, and demonstrated effectiveness in word analogy, similarity tests, and downstream tasks like Korean news headline generation.
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.