Semi-supervised disentangled framework for transferable named entity recognition

Named entity recognition (NER) for identifying proper nouns in unstructured text is one of the most important and fundamental tasks natural language processing. However, despite widespread use NER models, they still require a large-scale labeled data set, which incurs heavy burden due to manual annotation. Domain adaptation promising solutions this problem, where rich from relevant source domain are utilized strengthen generalizability model based on target domain. mainstream cross-domain models affected by following two challenges (1) Extracting domain-invariant information such as syntactic transfer. (2) Integrating domain-specific semantic into improve performance NER. In study, we present semi-supervised framework transferable NER, disentangles latent variables variables. proposed framework, integrated with using predictor. The disentangled three mutual regularization terms, i.e., maximizing between original embedding, minimizing Extensive experiments demonstrated that our can obtain state-of-the-art cross-lingual benchmark sets.