Ancient Korean Archive Translation: Comparison Analysis on Statistical phrase alignment, LLM in-context learning, and inter-methodological approach
Computation and Language
2024-07-17 v1
Abstract
This study aims to compare three methods for translating ancient texts with sparse corpora: (1) the traditional statistical translation method of phrase alignment, (2) in-context LLM learning, and (3) proposed inter methodological approach - statistical machine translation method using sentence piece tokens derived from unified set of source-target corpus. The performance of the proposed approach in this study is 36.71 in BLEU score, surpassing the scores of SOLAR-10.7B context learning and the best existing Seq2Seq model. Further analysis and discussion are presented.
Keywords
Cite
@article{arxiv.2407.11368,
title = {Ancient Korean Archive Translation: Comparison Analysis on Statistical phrase alignment, LLM in-context learning, and inter-methodological approach},
author = {Sojung Lucia Kim and Taehong Jang and Joonmo Ahn},
journal= {arXiv preprint arXiv:2407.11368},
year = {2024}
}
Comments
ACL2024 submitted