MNER-QG: An End-to-End MRC Framework for Multimodal Named Entity Recognition with Query Grounding

Multimodal named entity recognition (MNER) is a critical step in information extraction, which aims to detect entity spans and classify them to corresponding entity types given a sentence-image pair. Existing methods either (1) obtain named entities with coarse-grained visual clues from attention mechanisms, or (2) first detect fine-grained visual regions with toolkits and then recognize named entities. However, they suffer from improper alignment between entity types and visual regions or error propagation in the two-stage manner, which finally imports irrelevant visual information into texts. In this paper, we propose a novel end-to-end framework named MNER-QG that can simultaneously perform MRC-based multimodal named entity recognition and query grounding. Specifically, with the assistance of queries, MNER-QG can provide prior knowledge of entity types and visual regions, and further enhance representations of both text and image. To conduct the query grounding task, we provide manual annotations and weak supervisions that are obtained via training a highly flexible visual grounding model with transfer learning. We conduct extensive experiments on two public MNER datasets, Twitter2015 and Twitter2017. Experimental results show that MNER-QG outperforms the current state-of-the-art models on the MNER task, and also improves the query grounding performance.

Authors

• Meihuizi Jia Beijing Institute of Technology
• Lei Shen Alibaba Group
• Xin Shen Australian National University
• Lejian Liao School of Computer Science, Beijing Institute of Technology
• Meng Chen Yep AI, Melbourne, Australia
• Xiaodong He JD AI, Beijing
• Zhendong Chen Beijing Institute of Technology
• Jiaqi Li Tsinghua University

Keywords

• CV: Multi-modal Vision
• DMKM: Mining of Visual, Multimedia & Multimodal Data
• ML: Multimodal Learning
• SNLP: Information Extraction
• SNLP: Language Grounding