A Sequence Modelling Approach to Question Answering in Text-Based Games

Gregory Furman, Edan Toledo, Jonathan Shock, Jan Buys


Abstract
Interactive Question Answering (IQA) requires an intelligent agent to interact with a dynamic environment in order to gather information necessary to answer a question. IQA tasks have been proposed as means of training systems to develop language or visual comprehension abilities. To this end, the Question Answering with Interactive Text (QAit) task was created to produce and benchmark interactive agents capable of seeking information and answering questions in unseen environments. While prior work has exclusively focused on IQA as a reinforcement learning problem, such methods suffer from low sample efficiency and poor accuracy in zero-shot evaluation. In this paper, we propose the use of the recently proposed Decision Transformer architecture to provide improvements upon prior baselines. By utilising a causally masked GPT-2 Transformer for command generation and a BERT model for question answer prediction, we show that the Decision Transformer achieves performance greater than or equal to current state-of-the-art RL baselines on the QAit task in a sample efficient manner. In addition, these results are achievable by training on sub-optimal random trajectories, therefore not requiring the use of online agents to gather data.
Anthology ID:
2022.wordplay-1.4
Volume:
Proceedings of the 3rd Wordplay: When Language Meets Games Workshop (Wordplay 2022)
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marc-Alexandre Côté, Xingdi Yuan, Prithviraj Ammanabrolu
Venue:
Wordplay
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
44–58
Language:
URL:
https://aclanthology.org/2022.wordplay-1.4
DOI:
10.18653/v1/2022.wordplay-1.4
Bibkey:
Cite (ACL):
Gregory Furman, Edan Toledo, Jonathan Shock, and Jan Buys. 2022. A Sequence Modelling Approach to Question Answering in Text-Based Games. In Proceedings of the 3rd Wordplay: When Language Meets Games Workshop (Wordplay 2022), pages 44–58, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
A Sequence Modelling Approach to Question Answering in Text-Based Games (Furman et al., Wordplay 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.wordplay-1.4.pdf