Integrating Text and Image: Determining Multimodal Document Intent in Instagram Posts

IJCNLP 2019 Julia KrukJonah LubinKaran SikkaXiao LinDan JurafskyAjay Divakaran

Computing author intent from multimodal data like Instagram posts requires modeling a complex relationship between text and image. For example, a caption might evoke an ironic contrast with the image, so neither caption nor image is a mere transcript of the other... (read more)

PDF Abstract

Evaluation Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.