Image-text discourse coherence relation discoveries on multi-image and multi-text documents
Hanzhong Zheng, Zhexiong Liu, Dejia Shi · Journal of Physics Conference Series · 2021
Abstract The occurrences of the image-text pairs are common in social media such as image captions, image annotations, and cooking instructions. However, the links between images and texts as well as the coherence relationship among them are always implicit. We developed a multi-modal approach by firstly establishing the links between image and text in an unsupervised way, then discovered their coherence relations through computational models of discourse to improve the consistency and quality of the images and their corresponding texts and also explore a dynamic and flexible image-text coherence relation.