Faster Zero-shot Multi-modal Entity Linking via Visual-Linguistic Representation

Multi-modal entity linking plays a crucial role in a wide range of knowledge-based modal-fusion tasks, i.e., multi-modal retrieval and multi-modal event extraction. We introduce the new (ZEMEL) task, the format is similar to multi-modal entity linking, but multi-modal mentions are linked to unseen e...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Data intelligence 2022-07, Vol.4 (3), p.493-508
Hauptverfasser:	Zheng, Qiushuo, Wen, Hao, Wang, Meng, Qi, Guilin, Bai, Chaoyu
Format:	Artikel
Sprache:	eng
Schlagworte:	Datasets Efficiency Knowledge Knowledge Graph Knowledge representation Linguistics Modal data Multi-modal Learning Multimedia Performance evaluation Poly Encoders
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!