Named Entity Recognition for Novel Types by Transfer Learning
This addresses the challenge of adapting NER models to new domains with different entity types, which is incremental as it builds on existing transfer learning approaches.
The paper tackles the problem of named entity recognition for novel types when training data is limited and labels mismatch across domains, proposing a transfer learning method to learn a domain-specific model using related domain data and a small in-domain dataset.
In named entity recognition, we often don't have a large in-domain training corpus or a knowledge base with adequate coverage to train a model directly. In this paper, we propose a method where, given training data in a related domain with similar (but not identical) named entity (NE) types and a small amount of in-domain training data, we use transfer learning to learn a domain-specific NE model. That is, the novelty in the task setup is that we assume not just domain mismatch, but also label mismatch.