ZS-MNET: A zero-shot learning based approach to multimodal named entity typing

Baohang Zhou, Ying Zhang, Kehui Song, Xuhui Sui, Yu Zhao, Xiaojie Yuan

Abstract: Highlights•Firstly propose a new task named zero-shot multimodal named entity typing.•Model fine-grained representations of multimodal data and types in a semantic space.•The experimental results demonstrate that ZS-MNET outperforms baseline approaches.