Which One? Leveraging Context Between Objects and Multiple Views for Language Grounding
Chancharik Mitra, Abrar Anwar, Rodolfo Corona, Dan Klein, Trevor Darrell, Jesse Thomason
Abstract
When connecting objects and their language referents in an embodied 3D environment, it is important to note that: (1) an object can be better characterized by leveraging comparative information between itself and other objects, and (2) an object’s appearance can vary with camera position. As such, we present the Multi-view Approach to Grounding in Context (MAGiC) model, which selects an object referent based on language that distinguishes between two similar objects. By pragmatically reasoning over both objects and across multiple views of those objects, MAGiC improves over the state-of-the-art model on the SNARE object reference task with a relative error reduction of 12.9% (representing an absolute improvement of 2.7%). Ablation studies show that reasoning jointly over object referent candidates and multiple views of each object both contribute to improved accuracy. Code: https://github.com/rcorona/magic_snare/
BibTeX
@inproceedings{mitra-etal-2024-one,
title = "Which One? Leveraging Context Between Objects and Multiple Views for Language Grounding",
author = "Mitra, Chancharik and
Anwar, Abrar and
Corona, Rodolfo and
Klein, Dan and
Darrell, Trevor and
Thomason, Jesse",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.175/",
doi = "10.18653/v1/2024.naacl-long.175",
pages = "3177--3189"
}