Task-oriented dialogue (ToD) systems have been mostly created for high-resource languages, such as English and Chinese. However, there is a need to develop ToD systems for other regional or local languages to broaden their ability to comprehend the dialogue contexts in various languages. This paper introduces IndoToD, an end-to-end multi domain ToD benchmark in Indonesian. We extend two English ToD datasets to Indonesian, comprising four different domains by delexicalization to efficiently reduce the size of annotations. To ensure a high-quality data collection, we hire native speakers to manually translate the dialogues. Along with the original English datasets, these new Indonesian datasets serve as an effective benchmark for evaluating Indonesian and English ToD systems as well as exploring the potential benefits of cross-lingual and bilingual transfer learning approaches.
@article{arxiv.2311.00958,
title = {IndoToD: A Multi-Domain Indonesian Benchmark For End-to-End Task-Oriented Dialogue Systems},
author = {Muhammad Dehan Al Kautsar and Rahmah Khoirussyifa' Nurdini and Samuel Cahyawijaya and Genta Indra Winata and Ayu Purwarianti},
journal= {arXiv preprint arXiv:2311.00958},
year = {2023}
}
Comments
2023 1st Workshop in South East Asian Language Processing (SEALP), Co-located with AACL 2023