Visually-Verifiable Textual Entailment: A Challenge Task for Combining Language and Vision
Jayant Krishnamurthy · 2015
We propose visually-verifiable textual entailment as a challenge task for the emerging field of combining language and vision.This task is a variant of the wellstudied NLP task of recognizing textual entailment (Dagan et al., 2006) where every entailment judgment can be made purely by reasoning with visual knowledge.We believe that this task will spur innovation in the language and vision field while simultaneously producing inference algorithms that can be used in NLP.