Towards an open-domain chatbot for language practice

Gladys Tyen, Mark Brenchley, Andrew Caines, Paula Buttery


Abstract
State-of-the-art chatbots for English are now able to hold conversations on virtually any topic (e.g. Adiwardana et al., 2020; Roller et al., 2021). However, existing dialogue systems in the language learning domain still use hand-crafted rules and pattern matching, and are much more limited in scope. In this paper, we make an initial foray into adapting open-domain dialogue generation for second language learning. We propose and implement decoding strategies that can adjust the difficulty level of the chatbot according to the learner’s needs, without requiring further training of the chatbot. These strategies are then evaluated using judgements from human examiners trained in language education. Our results show that re-ranking candidate outputs is a particularly effective strategy, and performance can be further improved by adding sub-token penalties and filtering.
Anthology ID:
2022.bea-1.28
Volume:
Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)
Month:
July
Year:
2022
Address:
Seattle, Washington
Editors:
Ekaterina Kochmar, Jill Burstein, Andrea Horbach, Ronja Laarmann-Quante, Nitin Madnani, Anaïs Tack, Victoria Yaneva, Zheng Yuan, Torsten Zesch
Venue:
BEA
SIG:
SIGEDU
Publisher:
Association for Computational Linguistics
Note:
Pages:
234–249
Language:
URL:
https://aclanthology.org/2022.bea-1.28
DOI:
10.18653/v1/2022.bea-1.28
Bibkey:
Cite (ACL):
Gladys Tyen, Mark Brenchley, Andrew Caines, and Paula Buttery. 2022. Towards an open-domain chatbot for language practice. In Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022), pages 234–249, Seattle, Washington. Association for Computational Linguistics.
Cite (Informal):
Towards an open-domain chatbot for language practice (Tyen et al., BEA 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.bea-1.28.pdf
Code
 whgtyen/controllablecomplexitychatbot