We describe the results of training state-of-the-art generative and retrieval models in this setting. Models and humans can both act as characters within the game. In it, agents can perceive, emote, and act whilst conducting dialogue with other agents.
Publisher = "Association for Computational Linguistics",Ībstract = "We introduce a large-scale crowdsourced text adventure game as a research platform for studying grounded dialogue.
#FANTASY PAGE ART TEXT MODS#
Cite (Informal): Learning to Speak and Act in a Fantasy Text Adventure Game (Urbanek et al., EMNLP 2019) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Attachment: = "Learning to Speak and Act in a Fantasy Text Adventure Game",īooktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)", Association for Computational Linguistics. 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), pages 673–683, Hong Kong, China. Learning to Speak and Act in a Fantasy Text Adventure Game. | IJCNLP SIG: SIGDAT Publisher: Association for Computational Linguistics Note: Pages: 673–683 Language: URL: DOI: 10.18653/v1/D19-1062 Bibkey: urbanek-etal-2019-learning Cite (ACL): Jack Urbanek, Angela Fan, Siddharth Karamcheti, Saachi Jain, Samuel Humeau, Emily Dinan, Tim Rocktäschel, Douwe Kiela, Arthur Szlam, and Jason Weston. Anthology ID: D19-1062 Volume: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) Month: November Year: 2019 Address: Hong Kong, China Venues: EMNLP 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. 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 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. Abstract We introduce a large-scale crowdsourced text adventure game as a research platform for studying grounded dialogue.
0 kommentar(er)
