Abstract
In this paper, we describe our TMU neural machine translation (NMT) system submitted for the Patent task (Korean→Japanese) of the 7th Workshop on Asian Translation (WAT 2020, Nakazawa et al., 2020). We propose a novel method to train a Korean-to-Japanese translation model. Specifically, we focus on the vocabulary overlap of Korean Hanja words and Japanese Kanji words, and propose strategies to leverage Hanja information. Our experiment shows that Hanja information is effective within a specific domain, leading to an improvement in the BLEU scores by +1.09 points compared to the baseline.- Anthology ID:
- 2020.wat-1.15
- Volume:
- Proceedings of the 7th Workshop on Asian Translation
- Month:
- December
- Year:
- 2020
- Address:
- Suzhou, China
- Venue:
- WAT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 127–134
- Language:
- URL:
- https://aclanthology.org/2020.wat-1.15
- DOI:
- Cite (ACL):
- Hwichan Kim, Tosho Hirasawa, and Mamoru Komachi. 2020. Korean-to-Japanese Neural Machine Translation System using Hanja Information. In Proceedings of the 7th Workshop on Asian Translation, pages 127–134, Suzhou, China. Association for Computational Linguistics.
- Cite (Informal):
- Korean-to-Japanese Neural Machine Translation System using Hanja Information (Kim et al., WAT 2020)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2020.wat-1.15.pdf