CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation.
Devaansh GuptaSiddhant KharbandaJiawei ZhouWanhua LiHanspeter PfisterDonglai WeiPublished in: ICCV (2023)
Keyphrases
- machine translation
- language independent
- cross language information retrieval
- pre trained
- cross lingual
- statistical translation models
- statistical models
- information extraction
- natural language processing
- knowledge base
- probabilistic model
- visual features
- visual information
- word alignment
- target language
- prior knowledge
- data mining
- multi modal
- translation model
- machine translation system
- word level
- text mining
- parallel corpus
- finite state transducers
- information retrieval