SRCB at SemEval-2023 Task 1: Prompt Based and Cross-Modal Retrieval Enhanced Visual Word Sense Disambiguation.
Xudong ZhangTiange ZhenJing ZhangYujin WangSong LiuPublished in: SemEval@ACL (2023)
Keyphrases
- cross modal
- word sense disambiguation
- multi modal
- wordnet
- multimedia retrieval
- visual similarity
- natural language processing
- image retrieval
- machine translation
- semantic similarity
- information extraction
- multimedia databases
- sense disambiguation
- visual data
- word sense
- visual recognition
- visual features
- high level
- semantic concepts
- semantic information
- machine learning methods
- machine learning
- feature set
- xml documents
- similarity measure
- multimedia
- knowledge base
- search engine