Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment.
Cong-Duy NguyenThe-Anh Vu-LeThong NguyenTho QuanAnh Tuan LuuPublished in: ACM Multimedia (2023)
Keyphrases
- language learning
- visual information
- audio visual
- visual content
- visual features
- foreign language
- visual data
- english language
- computer assisted language learning
- visual cues
- mobile learning
- low level
- language acquisition
- multi modal
- textual information
- eye movements
- image representation
- databases
- multimedia
- database
- visual input
- mobile language learning