MultiModalQA: complex question answering over text, tables and images.
Alon TalmorOri YoranAmnon CatavDan LahavYizhong WangAkari AsaiGabriel IlharcoHannaneh HajishirziJonathan BerantPublished in: ICLR (2021)
Keyphrases
- question answering
- syntactic information
- information retrieval
- information extraction
- text summarization
- natural language processing
- named entities
- database
- textual entailment recognition
- image classification
- image retrieval
- sentence retrieval
- free text
- natural language
- question classification
- qa clef
- text retrieval
- image annotation
- cross language
- relation extraction
- semantic role labeling
- question answering systems
- speech transcripts
- keywords