Enhancing Multimodal Entity and Relation Extraction With Variational Information Bottleneck
Shiyao Cui, Jiangxia Cao, Xin Cong, Jiawei Sheng, Quangang Li, Tingwen Liu, Jinqiao Shi
Abstract
This paper studies the multimodal named entity recognition (MNER) and multimodal relation extraction (MRE), which are important for content analysis and various applications. The core of MNER and MRE lies in incorporating evident visual information to enhance textual semantics, where two issues inherently demand investigations. The first issue is modality-noise, where the task-irrelevant information in each modality may be noises misleading the task prediction. The second issue is modality-gap, where representations from different modalities are inconsistent, preventing from building the semantic alignment between the text and image. To address these issues, we propose a novel method for MNER and MRE by <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</u> ulti <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</u> odal representation learning with <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</u> nformation <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</u> ottleneck (MMIB). For the first issue, a refinement-regularizer probes the information-bottleneck principle to balance the predictive evidence and noisy information, yielding expressive representations for prediction. For the second issue, an alignment-regularizer is proposed, where a mutual information-based item works in a contrastive manner to regularize the consistent text-image representations. To our best knowledge, we are the first to explore variational IB estimation for MNER and MRE. Experiments show that MMIB achieves the state-of-the-art performances on three public benchmarks.