Cross-Domain Bootstrapping for Named Entity Recognition

We propose a general cross-domain bootstrapping algorithm for domain adaptation in the task of named entity recognition. We first generalize the lexical features of the source domain model with word clusters generated from a joint corpus. We then select target domain instances based on multiple criteria during the bootstrapping process. Without using annotated data from the target domain and without explicitly encoding any target-domainspecific knowledge, we were able to improve the source model’s F-measure by 7 points on the target domain.