@inproceedings{e1cce319cf0f42408063b13d75f314c3,
title = "KpopMT: Translation Dataset with Terminology for Kpop Fandom",
abstract = "While machines learn from existing corpora, humans have the unique capability to establish and accept new language systems. This makes human form unique language systems within social groups. Aligning with this, we focus on a gap remaining in addressing translation challenges within social groups, where in-group members utilize unique terminologies. We propose KpopMT dataset, which aims to fill this gap by enabling precise terminology translation, choosing Kpop fandom as an initiative for social groups given its global popularity. Expert translators provide 1k English translations for Korean posts and comments, each annotated with specific terminology within social groups' language systems. We evaluate existing translation systems including GPT models on KpopMT to identify their failure cases. Results show overall low scores, underscoring the challenges of reflecting group-specific terminologies and styles in translation. We make KpopMT publicly available.",
author = "Kim, \{Ji Woo\} and Yunsu Kim and Bak, \{Jin Yeong\}",
note = "Publisher Copyright: {\textcopyright} 2024 Association for Computational Linguistics.; 7th Workshop on Technologies for Machine Translation of Low-Resource Languages, LoResMT 2024 at ACL 2024 ; Conference date: 15-08-2024",
year = "2024",
language = "English",
series = "LoResMT 2024 - 7th Workshop on Technologies for Machine Translation of Low-Resource Languages, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "109--120",
editor = "Ojha, \{Atul Kr.\} and Ojha, \{Atul Kr.\} and Chao-hong Liu and Ekaterina Vylomova and Flammie Pirinen and Jade Abbott and Jonathan Washington and Nathaniel Oco and Valentin Malykh and Logacheva, \{Varvara Skolkovo\} and Xiaobing Zhao",
booktitle = "LoResMT 2024 - 7th Workshop on Technologies for Machine Translation of Low-Resource Languages, Proceedings of the Workshop",
}