A Sub-Character Architecture for Korean Language Processing

Karl Stratos


Abstract
We introduce a novel sub-character architecture that exploits a unique compositional structure of the Korean language. Our method decomposes each character into a small set of primitive phonetic units called jamo letters from which character- and word-level representations are induced. The jamo letters divulge syntactic and semantic information that is difficult to access with conventional character-level units. They greatly alleviate the data sparsity problem, reducing the observation space to 1.6% of the original while increasing accuracy in our experiments. We apply our architecture to dependency parsing and achieve dramatic improvement over strong lexical baselines.
Anthology ID:
D17-1075
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
721–726
Language:
URL:
https://aclanthology.org/D17-1075
DOI:
10.18653/v1/D17-1075
Bibkey:
Cite (ACL):
Karl Stratos. 2017. A Sub-Character Architecture for Korean Language Processing. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 721–726, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
A Sub-Character Architecture for Korean Language Processing (Stratos, EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1075.pdf
Code
 karlstratos/koreannet