Evaluating the Use of Generative LLMs for Intralingual Diachronic Translation of Middle-Polish Texts into Contemporary Polish

被引：0

作者：

Klamra, Cezary ^{[1
]}

Krynska, Katarzyna ^{[2
]}

Ogrodniczuk, Maciej ^{[1
]}

机构：

[1] Polish Acad Sci, Inst Comp Sci, Jana Kazimierza 5, PL-01248 Warsaw, Poland

[2] Polish Acad Sci, Inst Polish Language, Al Mickiewicza 31, PL-31120 Krakow, Poland

来源：

LEVERAGING GENERATIVE INTELLIGENCE IN DIGITAL LIBRARIES: TOWARDS HUMAN-MACHINE COLLABORATION, ICADL 2023, PT I | 2023年 / 14457卷

关键词：

Intralingual diachronic translation; Automatic annotation; Large Language Models;

D O I：

10.1007/978-981-99-8085-7_2

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents efforts towards creating a tool for translating texts from Middle Polish into modern Polish. Archaic texts sourced from the CBDU digital library were translated into modern language using ChatGPT and the resulting parallel corpus was used to train a neural text-to-text model. We assessed the results using automatic metrics and performed human evaluation of translations of the best-performing model and ChatGPT. Even though the performance of the trained models was far from perfect, the quality of translations produced with ChatGPT was good in most cases. Although caution should be exercised, we believe that LLMs have a high potential for text-to-text annotation applications.

引用

页码：18 / 27

页数：10