Can images help recognize entities? A study of the role of images for Multimodal NER

Shuguang Chen, Gustavo Aguilar, Leonardo Neves, Thamar Solorio


Abstract
Multimodal named entity recognition (MNER) requires to bridge the gap between language understanding and visual context. While many multimodal neural techniques have been proposed to incorporate images into the MNER task, the model’s ability to leverage multimodal interactions remains poorly understood. In this work, we conduct in-depth analyses of existing multimodal fusion techniques from different perspectives and describe the scenarios where adding information from the image does not always boost performance. We also study the use of captions as a way to enrich the context for MNER. Experiments on three datasets from popular social platforms expose the bottleneck of existing multimodal models and the situations where using captions is beneficial.
Anthology ID:
2021.wnut-1.11
Volume:
Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
Month:
November
Year:
2021
Address:
Online
Venues:
EMNLP | WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
87–96
Language:
URL:
https://aclanthology.org/2021.wnut-1.11
DOI:
10.18653/v1/2021.wnut-1.11
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.wnut-1.11.pdf
Code
 RiTUAL-UH/multimodal_NER