VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering.
Catalina CangeaEugene BelilovskyPietro LiòAaron C. CourvillePublished in: ViGIL@NeurIPS (2019)
Keyphrases
- question answering
- information extraction
- information retrieval
- natural language processing
- natural language
- visual features
- natural language questions
- qa clef
- question classification
- relation extraction
- visual information
- open domain question answering
- passage retrieval
- question answering systems
- named entities
- answer extraction
- cross language
- semantic roles
- sentence retrieval
- answering questions
- answer validation
- data mining
- syntactic information
- probabilistic model
- low level