MMToM-QA: Multimodal Theory of Mind Question Answering.
Chuanyang JinYutong WuJing CaoJiannan XiangYen-Ling KuoZhiting HuTomer D. UllmanAntonio TorralbaJoshua B. TenenbaumTianmin ShuPublished in: CoRR (2024)
Keyphrases
- question answering
- qa systems
- multi modal
- qa clef
- question classification
- natural language
- natural language processing
- information extraction
- cross language
- question answering systems
- passage retrieval
- information retrieval
- named entities
- relation extraction
- open domain
- answering questions
- natural language questions
- answer validation
- candidate answers
- semantic roles
- answer extraction
- audio visual
- text classification
- relational databases
- search engine