Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

7-2020

Abstract

In this paper, we study Multimodal Named Entity Recognition (MNER) for social media posts. Existing approaches for MNER mainly suffer from two drawbacks: (1) despite generating word-aware visual representations, their word representations are insensitive to the visual context; (2) most of them ignore the bias brought by the visual context. To tackle the first issue, we propose a multimodal interaction module to obtain both image-aware word representations and word-aware visual representations. To alleviate the visual bias, we further propose to leverage purely text-based entity span detection as an auxiliary module, and design a Unified Multimodal Transformer to guide the final predictions with the entity span predictions. Experiments show that our unified approach achieves the new state-of-the-art performance on two benchmark datasets.

Discipline

Databases and Information Systems | Theory and Algorithms

Research Areas

Data Science and Engineering

Publication

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

First Page

3342

Last Page

3352

Identifier

10.18653/v1/2020.acl-main.306

Publisher

Association for Computational Linguistics

City or Country

Online

Additional URL

https://doi.org/10.18653/v1/2020.acl-main.306

Share

COinS