[3R5-OS-31] OS-31

[3R5-OS-31-04] Scenario translation using large-scale language models and GraphRAG

〇Takayuki Shimotomai¹, Jukiya Noda¹, Takushi Kodani¹, Tomoki Takekawa¹, Ryuto Ikeuchi¹, Fuka Shibata¹, Koki Takeishi¹ (1. Headwaters inc.)

Keywords:Machine translation, Knowledge graph, Large language model, scenario, character

Expanding games overseas is important but requires a lot of costs, with language translation being a key issue.
Stories and scenarios are generally long, so maintaining consistency is a key issue in automatic translation.
Maintaining a worldview that includes character and cultural background is also an important element.
In this study, we propose a translation method for scenario that uses a GraphRAG and large-scale language model.
We evaluate character consistency to demonstrate the effectiveness of the proposed method.