Multimodal Logical Inference System for Visual-Textual Entailment.

Riko Suzuki Hitomi Yanaka Masashi Yoshikawa Koji Mineshima Daisuke Bekki

Published in: ACL (2) (2019)

Keyphrases

textual entailment
answer validation exercise
recognizing textual entailment
visual information
semantic features
visual features
lexico syntactic
machine learning
natural language processing
answer validation
high level
information retrieval systems
wordnet