An Alignment and Matching Network with Hierarchical Visual Features for Multimodal Named Entity and Relation Extraction.
Yinglong DaiFeng GaoDaojian ZengPublished in: ICONIP (12) (2023)
Keyphrases
- relation extraction
- visual features
- named entities
- semantic features
- information extraction
- named entity recognition
- image classification
- visual information
- annotated corpus
- low level features
- image annotation
- domain specific
- question answering
- image retrieval
- co occurrence
- automatic extraction
- low level
- semantic relations
- named entity recognizer
- text mining
- keywords
- text documents
- natural language processing
- key frames
- unsupervised learning
- knowledge sources
- wordnet
- text classification
- active learning
- noun phrases
- face recognition
- information retrieval