Learning Dictionaries for Named Entity Recognition using Minimal Supervision
This work addresses the challenge of reducing annotation effort for NER in specific domains, presenting an incremental improvement over existing methods.
The paper tackles the problem of constructing dictionaries for Named Entity Recognition with minimal supervision, using unlabeled data and seed examples, and reports improvements of 16.5% and 11.3% F-1 score over co-training on disease and virus NER tasks.
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.