Learning Dictionaries for Named Entity Recognition using Minimal Supervision
Computation and Language
2015-04-28 v1 Machine Learning
Abstract
This paper describes an approach for automatic construction of dictionaries for Named Entity Recognition (NER) using large amounts of unlabeled data and a few seed examples. We use Canonical Correlation Analysis (CCA) to obtain lower dimensional embeddings (representations) for candidate phrases and classify these phrases using a small number of labeled examples. Our method achieves 16.5% and 11.3% F-1 score improvement over co-training on disease and virus NER respectively. We also show that by adding candidate phrase embeddings as features in a sequence tagger gives better performance compared to using word embeddings.
Cite
@article{arxiv.1504.06650,
title = {Learning Dictionaries for Named Entity Recognition using Minimal Supervision},
author = {Arvind Neelakantan and Michael Collins},
journal= {arXiv preprint arXiv:1504.06650},
year = {2015}
}
Comments
In 14th Conference of the European Chapter of the Association for Computational Linguistic, 2014