Exploring Features for Named Entity Recognition in Lithuanian Text Corpus.
Jurgita Kapociute-DzikieneAnders NøklestadJanne Bondi JohannessenAlgis KrupaviciusPublished in: NODALIDA (2013)
Keyphrases
- named entity recognition
- named entities
- text corpus
- information extraction
- maximum entropy classifier
- natural language processing
- co occurrence
- text summarization
- maximum entropy
- conditional random fields
- semi supervised
- feature set
- databases
- feature space
- information retrieval
- maximum likelihood
- prior knowledge
- feature extraction