SceneGATE: Scene-Graph Based Co-Attention Networks for Text Visual Question Answering.
Feiqi CaoSiwen LuoFelipe NunezZean WenJosiah PoonSoyeon Caren HanPublished in: Robotics (2023)
Keyphrases
- query expansion
- question answering
- information retrieval
- text retrieval
- passage retrieval
- text summarization
- syntactic information
- cross language
- sentence retrieval
- visual data
- information extraction
- question classification
- relation extraction
- video sequences
- visual information
- natural language text
- textual entailment recognition
- text mining
- natural language
- natural language questions
- qa clef
- semantic parsing
- natural language processing
- question answering systems
- named entities
- search engine
- semi supervised
- video search
- visual features
- document retrieval
- answer extraction
- knowledge base
- answer validation
- question answer pairs
- free text