2019 ACL ACL 2019

A Corpus for Reasoning about Natural Language Grounded in Photographs

Abstract

AbstractWe introduce a new dataset for joint reasoning about natural language and images, with a focus on semantic diversity, compositionality, and visual reasoning challenges. The data contains 107,292 examples of English sentences paired with web photographs. The task is to determine whether a natural language caption is true about a pair of photographs. We crowdsource the data using sets of visually rich images and a compare-and-contrast task to elicit linguistically diverse language. Qualitative analysis shows the data requires compositional joint reasoning, including about quantities, comparisons, and relations. Evaluation using state-of-the-art visual reasoning methods shows the data presents a strong challenge.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Machine Learning and Natural Language Processing
📈 Trend Setter — Machine Reading Comprehension
🧭 Keyword Pioneer — joint reasoning
🐝 Cross-Pollinator — Artificial Intelligence, Computer Vision, Deep Learning, Machine Learning, Natural Language Processing, Reinforcement Learning, Robotics
🐣 Hot Topic Early Bird — compositional reasoning