Fusion of Detected Objects in Text for Visual Question Answering.
Chris AlbertiJeffrey LingMichael CollinsDavid ReitterPublished in: EMNLP/IJCNLP (1) (2019)
Keyphrases
- question answering
- information retrieval
- syntactic information
- text summarization
- information extraction
- textual entailment recognition
- named entities
- qa clef
- natural language processing
- question classification
- question answering systems
- semantic parsing
- text documents
- text retrieval
- cross language
- answer validation
- artificial intelligence
- natural language
- visual data
- open domain question answering
- question answer pairs
- passage retrieval
- visual information
- sentence retrieval
- text mining
- keywords
- natural language questions
- answering questions
- visual features
- video search
- relational databases
- answer extraction
- free text
- news video
- relation extraction