Retrieval Augmented Visual Question Answering with Outside Knowledge

Weizhe Lin, Bill Byrne


Abstract
Outside-Knowledge Visual Question Answering (OK-VQA) is a challenging VQA task that requires retrieval of external knowledge to answer questions about images. Recent OK-VQA systems use Dense Passage Retrieval (DPR) to retrieve documents from external knowledge bases, such as Wikipedia, but with DPR trained separately from answer generation, introducing a potential limit on the overall system performance.Instead, we propose a joint training scheme which includes differentiable DPR integrated with answer generation so that the system can be trained in an end-to-end fashion. Our experiments show that our scheme outperforms recent OK-VQA systems with strong DPR for retrieval. We also introduce new diagnostic metrics to analyze how retrieval and generation interact. The strong retrieval ability of our model significantly reduces the number of retrieved documents needed in training, yielding significant benefits in answer quality and computation required for training.
Anthology ID:
2022.emnlp-main.772
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11238–11254
Language:
URL:
https://aclanthology.org/2022.emnlp-main.772
DOI:
10.18653/v1/2022.emnlp-main.772
Bibkey:
Cite (ACL):
Weizhe Lin and Bill Byrne. 2022. Retrieval Augmented Visual Question Answering with Outside Knowledge. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11238–11254, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Retrieval Augmented Visual Question Answering with Outside Knowledge (Lin & Byrne, EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.772.pdf