Document detail
ID
oai:arXiv.org:2410.03959
Topic
Computer Science - Computation and... Computer Science - Artificial Inte... Computer Science - Computer Vision... Computer Science - GraphicsAuthor
Tang, Zineng Mao, Lingjun Suhr, AlaneCategory
Computer Science
Year
2024
listing date
10/9/2024
Keywords
model paired comprehension science computerAbstract
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 58.9 to 69.3% in communicative success and even outperforming the strongest proprietary model.
;Comment: Accepted to EMNLP2024 Main
Tang, Zineng,Mao, Lingjun,Suhr, Alane, 2024, Grounding Language in Multi-Perspective Referential Communication
Systematic Feature Design for Cycle Life Prediction of Lithium-Ion Batteries During Formation
cycle prediction framework feature design features life formation
