Semi-supervised learning for named entity recognition using weakly labeled training data
Authors:
- 1 March 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 129-135
Abstract
The shortage of the annotated training data is still an important challenge to building many Natural Language Process (NLP) tasks such as Named Entity Recognition. NER requires a large amount of training data with a high degree of human supervision whereas there is not enough labeled data for every language. In this paper, we use an unlabeled bilingual corpora to extract useful features from transferring information from resource-rich language toward resource-poor language and by using these features and a small training data, make a NER supervised model. Then we utilize a graph-based semi-supervised learning method that trains a CRF-based supervised classifier using that labeled data and uses high-confidence predictions on the unlabeled data to expand the training set and improve efficiency of NER model with the new training set.Keywords
This publication has 7 references indexed in Scilit:
- Biomedical named entity recognition using conditional random fields and rich feature sets2004
- Japanese Named Entity extraction with redundant morphological analysis2003
- Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons2003
- Named entity recognition2002
- Inducing multilingual text analysis tools via robust projection across aligned corpora2001
- Nymble1997
- Unsupervised word sense disambiguation rivaling supervised methods1995