The reviewed record of science sign in
Pith

arxiv: 2308.02570 · v1 · pith:NFH7QG2X · submitted 2023-08-03 · cs.LG · cs.AI· cs.CL· cs.CV

Learning Implicit Entity-object Relations by Bidirectional Generative Alignment for Multimodal NER

Reviewed by Pithpith:NFH7QG2Xopen to challenge →

classification cs.LG cs.AIcs.CLcs.CV
keywords bidirectionalentity-objectgenerationimageimplicitrelationsalignmentbga-mner
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.