Use of named entity recognition and co-reference resolution tools for segmenting english texts.
Pavlina FragkouPublished in: Panhellenic Conference on Informatics (2015)
Keyphrases
- named entity recognition
- information extraction
- natural language processing
- linguistic features
- named entities
- proper names
- natural language
- maximum entropy
- named entity recognizer
- conditional random fields
- text summarization
- semi supervised
- machine translation
- genia corpus
- linguistic analysis
- relation extraction
- natural language text
- text documents
- classifier ensemble
- annotated corpus
- maximum entropy classifier
- text mining
- pos tagging
- databases
- learning algorithm
- e learning
- image segmentation
- hidden markov models
- query translation
- higher order
- unsupervised learning