Multimodal named entity recognition with bottleneck fusion and contrastive learning
P Wang, X Chen, Z Shang, W Ke - IEICE TRANSACTIONS on …, 2023 - search.ieice.org
P Wang, X Chen, Z Shang, W Ke
IEICE TRANSACTIONS on Information and Systems, 2023•search.ieice.orgMultimodal named entity recognition (MNER) is the task of recognizing named entities in
multimodal context. Existing methods focus on utilizing co-attention mechanism to discover
the relationships between multiple modalities. However, they still have two deficiencies:
First, current methods fail to fuse the multimodal representations in a fine-grained way,
which may bring noise of visual modalities. Second, current methods ignore bridging the
semantic gap between heterogeneous modalities. To solve the above issues, we propose a …
multimodal context. Existing methods focus on utilizing co-attention mechanism to discover
the relationships between multiple modalities. However, they still have two deficiencies:
First, current methods fail to fuse the multimodal representations in a fine-grained way,
which may bring noise of visual modalities. Second, current methods ignore bridging the
semantic gap between heterogeneous modalities. To solve the above issues, we propose a …
Multimodal named entity recognition (MNER) is the task of recognizing named entities in multimodal context. Existing methods focus on utilizing co-attention mechanism to discover the relationships between multiple modalities. However, they still have two deficiencies: First, current methods fail to fuse the multimodal representations in a fine-grained way, which may bring noise of visual modalities. Second, current methods ignore bridging the semantic gap between heterogeneous modalities. To solve the above issues, we propose a novel MNER method with bottleneck fusion and contrastive learning (BFCL). Specifically, we first incorporate the transformer-based bottleneck fusion mechanism, subsequently, information between different modalities can only be exchanged through several bottleneck tokens, thus reducing the noise propagation. Then we propose two decoupled image-text contrastive losses to align the unimodal representations, making the representations of semantically similar modalities closer, while the representations of semantically different modalities farther away. Experimental results demonstrate that our method is competitive to the state-of-the-art models, and achieves 74.54% and 85.70% F1-scores on Twitter-2015 and Twitter-2017 datasets, respectively.
search.ieice.org