RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER

TL;DR

RpBERT enhances multimodal NER by selectively propagating relevant visual clues using relation-aware gates, significantly improving accuracy on tweet datasets.

Contribution

This paper introduces a novel text-image relation propagation mechanism with gating and multitask training for multimodal BERT in NER tasks.

Findings

Achieves state-of-the-art results on MNER datasets.

Effectively filters irrelevant visual clues, improving model focus.

Deep analysis of visual attention changes confirms the method's effectiveness.

Abstract

Recently multimodal named entity recognition (MNER) has utilized images to improve the accuracy of NER in tweets. However, most of the multimodal methods use attention mechanisms to extract visual clues regardless of whether the text and image are relevant. Practically, the irrelevant text-image pairs account for a large proportion in tweets. The visual clues that are unrelated to the texts will exert uncertain or even negative effects on multimodal model learning. In this paper, we introduce a method of text-image relation propagation into the multimodal BERT model. We integrate soft or hard gates to select visual clues and propose a multitask algorithm to train on the MNER datasets. In the experiments, we deeply analyze the changes in visual attention before and after the use of text-image relation propagation. Our model achieves state-of-the-art performance on the MNER datasets.