Development of a hindi named entity recognition system without using manually annotated training corpus.
Sujan Kumar SahaMukta MajumderPublished in: Int. Arab J. Inf. Technol. (2018)
Keyphrases
- relation extraction
- manually annotated
- named entities
- named entity recognition
- information extraction
- training corpus
- automatic extraction
- annotated corpus
- text mining
- domain specific
- semantic relations
- question answering
- co occurrence
- natural language processing
- semantic features
- text classification
- semi supervised
- machine learning
- maximum entropy
- text documents
- conditional random fields
- artificial intelligence
- maximum likelihood
- active learning
- training data
- feature extraction
- statistical machine translation
- information retrieval
- data mining