VISA: An Ambiguous Subtitles Dataset for Visual Scene-aware Machine Translation.
Yihang LiShuichiro ShimizuWeiqi GuChenhui ChuSadao KurohashiPublished in: LREC (2022)
Keyphrases
- machine translation
- visual scene
- language independent
- visual information
- information extraction
- visual attention
- target language
- cross language information retrieval
- vision system
- word alignment
- cross lingual
- language resources
- complex scenes
- object recognition
- natural language processing
- word level
- natural language
- natural images
- chinese english
- word sense disambiguation
- machine translation system
- statistical machine translation
- computer vision
- natural scenes
- image processing
- artificial intelligence
- multiscale
- information retrieval
- source language
- feature vectors
- machine learning
- knn
- data mining