Natural Language Processing for Multilingual Task-Oriented Dialogue

Evgeniia Razumovskaia, Goran Glavaš, Olga Majewska, Edoardo Ponti, Ivan Vulić


Abstract
Recent advances in deep learning have also enabled fast progress in the research of task-oriented dialogue (ToD) systems. However, the majority of ToD systems are developed for English and merely a handful of other widely spoken languages, e.g., Chinese and German. This hugely limits the global reach and, consequently, transformative socioeconomic potential of such systems. In this tutorial, we will thus discuss and demonstrate the importance of (building) multilingual ToD systems, and then provide a systematic overview of current research gaps, challenges and initiatives related to multilingual ToD systems, with a particular focus on their connections to current research and challenges in multilingual and low-resource NLP. The tutorial will aim to provide answers or shed new light to the following questions: a) Why are multilingual dialogue systems so hard to build: what makes multilinguality for dialogue more challenging than for other NLP applications and tasks? b) What are the best existing methods and datasets for multilingual and cross-lingual (task-oriented) dialog systems? How are (multilingual) ToD systems usually evaluated? c) What are the promising future directions for multilingual ToD research: where can one draw inspiration from related NLP areas and tasks?
Anthology ID:
2022.acl-tutorials.8
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Luciana Benotti, Naoaki Okazaki, Yves Scherrer, Marcos Zampieri
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
44–50
Language:
URL:
https://aclanthology.org/2022.acl-tutorials.8
DOI:
10.18653/v1/2022.acl-tutorials.8
Bibkey:
Cite (ACL):
Evgeniia Razumovskaia, Goran Glavaš, Olga Majewska, Edoardo Ponti, and Ivan Vulić. 2022. Natural Language Processing for Multilingual Task-Oriented Dialogue. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts, pages 44–50, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Natural Language Processing for Multilingual Task-Oriented Dialogue (Razumovskaia et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-tutorials.8.pdf