Incorporating Probing Signals into Multimodal Machine Translation via Visual Question-Answering Pairs.
Yuxin ZuoBei LiChuanhao LvTong ZhengTong XiaoJingbo ZhuPublished in: CoRR (2023)
Keyphrases
- question answering
- machine translation
- natural language processing
- information extraction
- natural language
- sentence retrieval
- language processing
- cross lingual
- information retrieval
- named entities
- question classification
- multi modal
- visual features
- qa clef
- visual information
- cross language
- cross language information retrieval
- machine learning
- statistical machine translation
- passage retrieval
- named entity recognition
- target language
- relation extraction
- text summarization
- machine translation system
- artificial intelligence
- query translation
- word sense disambiguation
- text mining
- semantic analysis
- semantic roles
- question answering systems
- precision and recall
- audio visual
- semantic relations