End-to-end Knowledge Retrieval with Multi-modal Queries

Man Luo, Zhiyuan Fang, Tejas Gokhale, Yezhou Yang, Chitta Baral


Abstract
We investigate knowledge retrieval with multi-modal queries, i.e. queries containing information split across image and text inputs, a challenging task that differs from previous work on cross-modal retrieval. We curate a new dataset called ReMuQ for benchmarking progress on this task. ReMuQ requires a system to retrieve knowledge from a large corpus by integrating contents from both text and image queries. We introduce a retriever model “ReViz” that can directly process input text and images to retrieve relevant knowledge in an end-to-end fashion without being dependent on intermediate modules such as object detectors or caption generators. We introduce a new pretraining task that is effective for learning knowledge retrieval with multimodal queries and also improves performance on downstream tasks. We demonstrate superior performance in retrieval on two datasets (ReMuQ and OK-VQA) under zero-shot settings as well as further improvements when finetuned on these datasets.
Anthology ID:
2023.acl-long.478
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8573–8589
Language:
URL:
https://aclanthology.org/2023.acl-long.478
DOI:
10.18653/v1/2023.acl-long.478
Bibkey:
Cite (ACL):
Man Luo, Zhiyuan Fang, Tejas Gokhale, Yezhou Yang, and Chitta Baral. 2023. End-to-end Knowledge Retrieval with Multi-modal Queries. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8573–8589, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
End-to-end Knowledge Retrieval with Multi-modal Queries (Luo et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.478.pdf
Video:
 https://aclanthology.org/2023.acl-long.478.mp4