US Patent Application 18201075. NAMED ENTITY RECOGNITION VISUAL CONTEXT AND CAPTION DATA simplified abstract

From WikiPatents
Jump to navigation Jump to search

NAMED ENTITY RECOGNITION VISUAL CONTEXT AND CAPTION DATA

Organization Name

Snap Inc.

Inventor(s)

Di Lu of Troy NY (US)

Leonardo Ribas Machado das Neves of Marina Del Rey CA (US)

Vitor Rocha de Carvalho of San Diego CA (US)

Ning Zhang of Los Angeles CA (US)

NAMED ENTITY RECOGNITION VISUAL CONTEXT AND CAPTION DATA - A simplified explanation of the abstract

This abstract first appeared for US patent application 18201075 titled 'NAMED ENTITY RECOGNITION VISUAL CONTEXT AND CAPTION DATA

Simplified Explanation

- The patent application is about a system that can identify named entities in captions of multimodal messages, such as social media posts. - The system uses an entity recognition system that incorporates a visual attention mechanism. - The visual attention mechanism generates a visual context representation from an image and caption. - The visual context representation is then used to identify one or more terms in the caption as named entities.


Original Abstract Submitted

A caption of a multimodal message (e.g., social media post) can be identified as a named entity using an entity recognition system. The entity recognition system can use a visual attention based mechanism to generate a visual context representation from an image and caption. The system can use the visual context representation to identify one or more terms of the caption as a named entity.