Learning Implicit Entity-object Relations by Bidirectional Generative Alignment for Multimodal NER
This work addresses the problem of implicit entity-object relations in multimodal named entity recognition for researchers in natural language processing and computer vision, representing an incremental improvement over existing methods.
The paper tackled the challenge of multimodal named entity recognition by addressing the semantic gap between text and image and matching entities with associated objects, proposing a bidirectional generative alignment method that achieved state-of-the-art performance on two benchmarks without requiring image input during inference.
The challenge posed by multimodal named entity recognition (MNER) is mainly two-fold: (1) bridging the semantic gap between text and image and (2) matching the entity with its associated object in image. Existing methods fail to capture the implicit entity-object relations, due to the lack of corresponding annotation. In this paper, we propose a bidirectional generative alignment method named BGA-MNER to tackle these issues. Our BGA-MNER consists of \texttt{image2text} and \texttt{text2image} generation with respect to entity-salient content in two modalities. It jointly optimizes the bidirectional reconstruction objectives, leading to aligning the implicit entity-object relations under such direct and powerful constraints. Furthermore, image-text pairs usually contain unmatched components which are noisy for generation. A stage-refined context sampler is proposed to extract the matched cross-modal content for generation. Extensive experiments on two benchmarks demonstrate that our method achieves state-of-the-art performance without image input during inference.