Aiding Intra-Text Representations with Visual Context for Multimodal Named Entity Recognition
This addresses entity recognition in social media for applications like content analysis, but it is incremental as it builds on existing multimodal methods.
The paper tackles the problem of named entity recognition in noisy, short social media posts by using images to resolve ambiguities, achieving state-of-the-art results on a Twitter multimodal dataset.
With massive explosion of social media such as Twitter and Instagram, people daily share billions of multimedia posts, containing images and text. Typically, text in these posts is short, informal and noisy, leading to ambiguities which can be resolved using images. In this paper we explore text-centric Named Entity Recognition task on these multimedia posts. We propose an end to end model which learns a joint representation of a text and an image. Our model extends multi-dimensional self attention technique, where now image helps to enhance relationship between words. Experiments show that our model is capable of capturing both textual and visual contexts with greater accuracy, achieving state-of-the-art results on Twitter multimodal Named Entity Recognition dataset.