VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation.
Linjie LiJie LeiZhe GanLicheng YuYen-Chun ChenRohit PillaiYu ChengLuowei ZhouXin WangWilliam Yang WangTamara L. BergMohit BansalJingjing LiuLijuan WangZicheng LiuPublished in: NeurIPS Datasets and Benchmarks (2021)
Keyphrases
- multi task
- language understanding
- multi task learning
- learning tasks
- natural language understanding
- gaussian processes
- multi class
- multiple tasks
- language processing
- feature selection
- general knowledge
- natural language
- learning problems
- learning experience
- k nearest neighbor
- supervised learning
- artificial intelligence