Faithful Multimodal Explanation for Visual Question Answering.
Jialin WuRaymond J. MooneyPublished in: BlackboxNLP@ACL (2019)
Keyphrases
- question answering
- information retrieval
- information extraction
- natural language processing
- syntactic information
- passage retrieval
- natural language
- question classification
- cross language
- question answering systems
- visual information
- qa clef
- named entities
- multi modal
- visual features
- multimedia
- natural language questions
- candidate answers
- open domain question answering
- relation extraction
- image classification
- answer extraction
- language model
- low level
- answer validation
- textual entailment recognition
- artificial intelligence