Collecting Interactive Multi-modal Datasets for Grounded Language Understanding.
Shrestha MohantyNegar ArabzadehMilagro TeruelYuxuan SunArtem ZholusAlexey SkrynnikMikhail S. BurtsevKavya SrinetAleksandr PanovArthur SzlamMarc-Alexandre CôtéJulia KiselevaPublished in: CoRR (2022)
Keyphrases
- multi modal
- language understanding
- natural language understanding
- multi modality
- semantic interpretation
- natural language
- user interaction
- language processing
- cross modal
- uni modal
- video search
- low level
- general knowledge
- high dimensional
- referring expressions
- dialogue system
- domain knowledge
- spoken dialogue systems
- metadata