OpenVNA: A Framework for Analyzing the Behavior of Multimodal Language Understanding System under Noisy Scenarios

Ziqi Yuan, Baozheng Zhang, Hua Xu, Zhiyun Liang, Kai Gao


Abstract
We present OpenVNA, an open-source framework designed for analyzing the behavior of multimodal language understanding systems under noisy conditions. OpenVNA serves as an intuitive toolkit tailored for researchers, facilitating convenience batch-level robustness evaluation and on-the-fly instance-level demonstration. It primarily features a benchmark Python library for assessing global model robustness, offering high flexibility and extensibility, thereby enabling customization with user-defined noise types and models. Additionally, a GUI-based interface has been developed to intuitively analyze local model behavior. In this paper, we delineate the design principles and utilization of the created library and GUI-based web platform. Currently, OpenVNA is publicly accessible at https://github.com/thuiar/OpenVNA, with a demonstration video available at https://youtu.be/0Z9cW7RGct4.
Anthology ID:
2024.acl-demos.2
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Yixin Cao, Yang Feng, Deyi Xiong
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9–18
Language:
URL:
https://aclanthology.org/2024.acl-demos.2
DOI:
10.18653/v1/2024.acl-demos.2
Bibkey:
Cite (ACL):
Ziqi Yuan, Baozheng Zhang, Hua Xu, Zhiyun Liang, and Kai Gao. 2024. OpenVNA: A Framework for Analyzing the Behavior of Multimodal Language Understanding System under Noisy Scenarios. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 9–18, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
OpenVNA: A Framework for Analyzing the Behavior of Multimodal Language Understanding System under Noisy Scenarios (Yuan et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-demos.2.pdf