Exploring the Necessity of Visual Modality in Multimodal Machine Translation using Authentic Datasets.
Zi LongZhenhao TangXianghua FuJian ChenShilong HouJinze LyuPublished in: CoRR (2024)
Keyphrases
- machine translation
- multi modal
- language independent
- natural language processing
- cross modal
- information extraction
- target language
- cross lingual
- cross language information retrieval
- natural language
- single modality
- language processing
- multiple modalities
- word level
- natural language generation
- language resources
- statistical machine translation
- machine translation system
- chinese english
- word sense disambiguation
- visual features
- word alignment
- brazilian portuguese
- query translation
- text mining
- image retrieval
- parallel corpora
- machine learning