From Captions to Explanations: A Multimodal Transformer-based Architecture for Natural Language Explanation Generation.
Isabel Rio-TortoJaime S. CardosoLuís F. TeixeiraPublished in: IbPRIA (2022)
Keyphrases
- natural language
- natural language interface
- generating explanations
- text generation
- multi modal
- knowledge representation
- management system
- natural language generation
- machine learning
- multimodal information
- data sets
- image search
- hardware implementation
- audio visual
- semantic analysis
- domain theory
- conceptual graphs
- natural language understanding
- video content
- semantic interpretation
- temporal information
- multimodal interaction
- visual features
- natural language processing