Grounding Language in Multi-Perspective Referential Communication
ZinengTang
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 58.9 to 69.3% in communicative success and even outperforming the strongest proprietary model.
Community
A spatial reasoning dataset with multi-agent communication.
Accepted to EMNLP 2024 Main
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.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- CoGen: Learning from Feedback with Coupled Comprehension and Generation (2024)
- Repairs in a Block World: A New Benchmark for Handling User Corrections with Multi-Modal Language Models (2024)
- Referring Expression Generation in Visually Grounded Dialogue with Discourse-aware Comprehension Guiding (2024)
- FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension (2024)
- EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper