arXiv Open Access 2024

Ancient Korean Archive Translation: Comparison Analysis on Statistical phrase alignment, LLM in-context learning, and inter-methodological approach

Sojung Lucia Kim Taehong Jang Joonmo Ahn

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CL

Penulis (3)

Sojung Lucia Kim

Taehong Jang

Joonmo Ahn

Format Sitasi

APA MLA BibTeX

Kim, S.L., Jang, T., Ahn, J. (2024). Ancient Korean Archive Translation: Comparison Analysis on Statistical phrase alignment, LLM in-context learning, and inter-methodological approach. https://arxiv.org/abs/2407.11368

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2024
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓