TY - GEN
T1 - Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction
AU - Li, Qian
AU - Guo, Shu
AU - Ji, Cheng
AU - Peng, Xutan
AU - Cui, Shiyao
AU - Li, Jianxin
AU - Wang, Lihong
N1 - Publisher Copyright:
© 2023 Association for Computational Linguistics.
PY - 2023
Y1 - 2023
N2 - Multi-Modal Relation Extraction (MMRE) aims at identifying the relation between two entities in texts that contain visual clues. Rich visual content is valuable for the MMRE task, but existing works cannot well model finer associations among different modalities, failing to capture the truly helpful visual information and thus limiting relation extraction performance. In this paper, we propose a novel MMRE framework to better capture the deeper correlations of text, entity pair, and image/objects, so as to mine more helpful information for the task, termed as DGF-PT. We first propose a prompt-based autoregressive encoder, which builds the associations of intra-modal and inter-modal features related to the task, respectively by entity-oriented and object-oriented prefixes. To better integrate helpful visual information, we design a dual-gated fusion module to distinguish the importance of image/objects and further enrich text representations. In addition, a generative decoder is introduced with entity type restriction on relations, better filtering out candidates. Extensive experiments conducted on the benchmark dataset show that our approach achieves excellent performance compared to strong competitors, even in the few-shot situation.
AB - Multi-Modal Relation Extraction (MMRE) aims at identifying the relation between two entities in texts that contain visual clues. Rich visual content is valuable for the MMRE task, but existing works cannot well model finer associations among different modalities, failing to capture the truly helpful visual information and thus limiting relation extraction performance. In this paper, we propose a novel MMRE framework to better capture the deeper correlations of text, entity pair, and image/objects, so as to mine more helpful information for the task, termed as DGF-PT. We first propose a prompt-based autoregressive encoder, which builds the associations of intra-modal and inter-modal features related to the task, respectively by entity-oriented and object-oriented prefixes. To better integrate helpful visual information, we design a dual-gated fusion module to distinguish the importance of image/objects and further enrich text representations. In addition, a generative decoder is introduced with entity type restriction on relations, better filtering out candidates. Extensive experiments conducted on the benchmark dataset show that our approach achieves excellent performance compared to strong competitors, even in the few-shot situation.
UR - https://www.scopus.com/pages/publications/85175472129
U2 - 10.18653/v1/2023.findings-acl.572
DO - 10.18653/v1/2023.findings-acl.572
M3 - 会议稿件
AN - SCOPUS:85175472129
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 8982
EP - 8994
BT - Findings of the Association for Computational Linguistics, ACL 2023
PB - Association for Computational Linguistics (ACL)
T2 - Findings of the Association for Computational Linguistics, ACL 2023
Y2 - 9 July 2023 through 14 July 2023
ER -