Into the Unknown: Generating Geospatial Descriptions for New Environments - ACL Anthology

Into the Unknown: Generating Geospatial Descriptions for New Environments

Tzuf Paz-Argaman, John Palowitch, Sayali Kulkarni, Reut Tsarfaty, Jason Baldridge


Abstract
Similar to vision-and-language navigation (VLN) tasks that focus on bridging the gap between vision and language for embodied navigation, the new Rendezvous (RVS) task requires reasoning over allocentric spatial relationships using non-sequential navigation instructions and maps. However, performance substantially drops in new environments with no training data.Using opensource descriptions paired with coordinates (e.g., Wikipedia) provides training data but suffers from limited spatially-oriented text resulting in low geolocation resolution. We propose a large-scale augmentation method for generating high-quality synthetic data for new environments using readily available geospatial data. Our method constructs a grounded knowledge-graph, capturing entity relationships. Sampled entities and relations (“shop north of school”) generate navigation instructions via (i) generating numerous templates using context-free grammar (CFG) to embed specific entities and relations; (ii) feeding the entities and relation into a large language model (LLM) for instruction generation. A comprehensive evaluation on RVS, showed that our approach improves the 100-meter accuracy by 45.83% on unseen environments. Furthermore, we demonstrate that models trained with CFG-based augmentation achieve superior performance compared with those trained with LLM-based augmentation, both in unseen and seen environments. These findings suggest that the potential advantages of explicitly structuring spatial information for text-based geospatial reasoning in previously unknown, can unlock data-scarce scenarios.
Anthology ID:
2024.findings-acl.133
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2259–2273
Language:
URL:
https://aclanthology.org/2024.findings-acl.133
DOI:
10.18653/v1/2024.findings-acl.133
Bibkey:
Cite (ACL):
Tzuf Paz-Argaman, John Palowitch, Sayali Kulkarni, Reut Tsarfaty, and Jason Baldridge. 2024. Into the Unknown: Generating Geospatial Descriptions for New Environments. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2259–2273, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Into the Unknown: Generating Geospatial Descriptions for New Environments (Paz-Argaman et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.133.pdf