Grounding Language in Multi-Perspective Referential Communication
Abstract: We introduce a task and dataset for referring expression generation and comprehension in multi-agent embodied environments.
In this task, two agents in a shared scene must take into account one another's visual perspective, which may be different from their own, to both produce and understand references to objects in a scene and the spatial relations between them. We collect a dataset of 2,970 human-written referring expressions, each paired with human comprehension judgments, and evaluate the performance of automated models as speakers and listeners paired with human partners, finding that model performance in both reference generation and comprehension lags behind that of pairs of human agents. Finally, we experiment training an open-weight speaker model with evidence of communicative success when paired with a listener, resulting in an improvement from 59.7 to 69.2\% in communicative success and even outperforming the strongest proprietary model.
Paper Type: Long
Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond
Research Area Keywords: language grounding, referring expression, embodiment, referential communication, multi-perspective, vision and language
Contribution Types: Data resources, Data analysis
Languages Studied: English
Submission Number: 4192
Loading