2019 LearningtoSpeakandActinaFantasy
- (Urbanek et al., 2019) ⇒ Jack Urbanek, Angela Fan, Siddharth Karamcheti, Saachi Jain, Samuel Humeau, Emily Dinan, Tim Rocktäschel, Douwe Kiela, Arthur Szlam, and Jason Weston. (2019). “Learning to Speak and Act in a Fantasy Text Adventure Game.” In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).
Subject Headings: LIGHT Game.
Notes
Cited By
Quotes
Abstract
We introduce a large-scale crowdsourced text adventure game as a research platform for studying grounded dialogue. In it, agents can perceive, emote, and act whilst conducting dialogue with other agents. Models and humans can both act as characters within the game. We describe the results of training state-of-the-art generative and retrieval models in this setting. We show that in addition to using past dialogue, these models are able to effectively use the state of the underlying world to condition their predictions. In particular, we show that grounding on the details of the local environment, including location descriptions, and the objects (and their affordances) and characters (and their previous actions) present within it allows better predictions of agent behavior and dialogue. We analyze the ingredients necessary for successful grounding in this setting, and how each of these factors relate to agents that can talk and act successfully.
References
;
Author | volume | Date Value | title | type | journal | titleUrl | doi | note | year | |
---|---|---|---|---|---|---|---|---|---|---|
2019 LearningtoSpeakandActinaFantasy | Jason Weston Tim Rocktäschel Angela Fan Arthur Szlam Jack Urbanek Siddharth Karamcheti Saachi Jain Samuel Humeau Emily Dinan Douwe Kiela | Learning to Speak and Act in a Fantasy Text Adventure Game | 2019 |