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.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. A good Samaritan in Tennessee reportedly helped rescue a woman in an alleged kidnapping and domestic violence situation after she used a hand signal popularized on TikTok. "If you see something, say something," witness Eric Streeval told WKRN. "Domestic violence is a bad thing here in Tennessee. The victims, a lot of times they're too afraid to speak out. And I credit the young lady in this situation with having the world's most courage of actually speaking out because who knows what would have happened."