English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multimodal named entity recognition (MNER) is a critical step in informationextraction, which aims to detect entity spans and classify them tocorresponding entity types given a sentence-image pair. Existing methods either(1) obtain named entities with coarse-grained visual clues from attentionmechanisms, or (2) first detect fine-grained visual regions with toolkits andthen recognize named entities. However, they suffer from improper alignmentbetween entity types and visual regions or error propagation in the two-stagemanner, which finally imports irrelevant visual information into texts. In thispaper, we propose a novel end-to-end framework named MNER-QG that cansimultaneously perform MRC-based multimodal named entity recognition and querygrounding. Specifically, with the assistance of queries, MNER-QG can provideprior knowledge of entity types and visual regions, and further enhancerepresentations of both texts and images. To conduct the query grounding task,we provide manual annotations and weak supervisions that are obtained viatraining a highly flexible visual grounding model with transfer learning. Weconduct extensive experiments on two public MNER datasets, Twitter2015 andTwitter2017. Experimental results show that MNER-QG outperforms the currentstate-of-the-art models on the MNER task, and also improves the query groundingperformance.

MNER-QG: An End-to-End MRC framework for Multimodal Named Entity Recognition with Query Grounding