End-To-End Named Entity And Semantic Concept Extraction From Speech.
Sahar GhannayAntoine CaubrièreYannick EstèveNathalie CamelinEdwin SimonnetAntoine LaurentEmmanuel MorinPublished in: SLT (2018)
Keyphrases
- end to end
- named entities
- semantic concepts
- information extraction
- text documents
- co occurrence
- relation extraction
- multi modal
- natural language processing
- semantic similarity
- text mining
- video analysis
- visual content
- low level
- low level features
- question answering
- visual features
- image collections
- visual concepts
- unsupervised learning
- multimedia content
- machine learning
- artificial intelligence
- image annotation
- video sequences
- visual information
- image content
- data analysis
- semantic information