Aiding Intra-Text Representations with Visual Context for Multimodal Named Entity Recognition.
Omer ArshadIgnazio GalloShah NawazAlessandro CalefatiPublished in: ICDAR (2019)
Keyphrases
- named entity recognition
- text summarization
- visual context
- named entities
- information extraction
- named entity disambiguation
- natural language processing
- named entity recognizer
- text mining
- semi supervised
- maximum entropy
- text documents
- conditional random fields
- semantic context
- temporal context
- object detection
- information retrieval
- question answering
- multi modal
- scene interpretation
- higher level
- image classification
- semantic information
- query expansion
- audio visual
- knowledge representation
- image retrieval
- data mining