Talk The Walk: Navigating Grids in New York City through Grounded Dialogue

Anonymous

Sep 27, 2018 ICLR 2019 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: We introduce `"Talk The Walk", the first large-scale dialogue dataset grounded in action and perception. The task involves two agents (a 'guide' and a 'tourist') that communicate via natural language in order to achieve a common goal: having the tourist navigate to a given target location. The task and dataset, which are described in detail, are challenging and their full solution is an open problem that we pose to the community. We (i) focus on the task of tourist localization and develop the novel Masked Attention for Spatial Convolutions (MASC) mechanism that allows for grounding tourist utterances into the guide's map, (ii) show it yields significant improvements for both emergent and natural language communication, and (iii) using this method, we establish non-trivial baselines on the full task.
  • Keywords: Dialogue, Navigation, Grounded Language Learning
  • TL;DR: First large-scale dialogue dataset grounded in action and perception
0 Replies

Loading