2018 NAACL NAACL 2018

Deep learning evaluation using deep linguistic processing

Abstract

AbstractWe discuss problems with the standard approaches to evaluation for tasks like visual question answering, and argue that artificial data can be used to address these as a complement to current practice. We demonstrate that with the help of existing β€˜deep’ linguistic processing technology we are able to create challenging abstract datasets, which enable us to investigate the language understanding abilities of multimodal deep learning models in detail, as compared to a single performance value on a static and monolithic dataset.

πŸŒ‰ Interdisciplinary Bridge β€” Artificial Intelligence and Machine Learning
🧭 Keyword Pioneer β€” artificial datum
🐣 Hot Topic Early Bird β€” language understanding
🐝 Cross-Pollinator β€” Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio