Look, Read and Enrich. Learning from Scientific Figures and their Captions

September 19, 2019 Β· Declared Dead Β· πŸ› International Conference on Knowledge Capture

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Jose Manuel Gomez-Perez, Raul Ortega arXiv ID 1909.09070 Category cs.AI: Artificial Intelligence Cross-listed cs.CL, cs.CV Citations 12 Venue International Conference on Knowledge Capture Last Checked 4 months ago
Abstract
Compared to natural images, understanding scientific figures is particularly hard for machines. However, there is a valuable source of information in scientific literature that until now has remained untapped: the correspondence between a figure and its caption. In this paper we investigate what can be learnt by looking at a large number of figures and reading their captions, and introduce a figure-caption correspondence learning task that makes use of our observations. Training visual and language networks without supervision other than pairs of unconstrained figures and captions is shown to successfully solve this task. We also show that transferring lexical and semantic knowledge from a knowledge graph significantly enriches the resulting features. Finally, we demonstrate the positive impact of such features in other tasks involving scientific text and figures, like multi-modal classification and machine comprehension for question answering, outperforming supervised baselines and ad-hoc approaches.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted