Towards named entity annotation of Latvian National Library corpus.
Peteris PaikensIlze AuzinaGinta GarkajeMadara PaeglePublished in: Baltic HLT (2012)
Keyphrases
- annotated corpus
- named entities
- national library
- digital libraries
- named entity recognition
- automatic annotation
- relation extraction
- linguistic features
- named entity extraction
- information extraction
- natural language processing
- text mining
- co occurrence
- question answering
- content based retrieval
- news corpus
- person names
- metadata
- unsupervised learning
- noun phrases
- object recognition
- weakly supervised
- machine translation
- text documents
- proper names
- text classification
- database
- named entity disambiguation