Neural Adaptation Layers for Cross-domain Named Entity Recognition
arXiv:1810.06368
Abstract
Recent research efforts have shown that neural architectures can be effective in conventional information extraction tasks such as named entity recognition, yielding state-of-the-art results on standard newswire datasets. However, despite significant resources required for training such models, the performance of a model trained on one domain typically degrades dramatically when applied to a different domain, yet extracting entities from new emerging domains such as social media can be of significant interest. In this paper, we empirically investigate effective methods for conveniently adapting an existing, well-trained neural NER model for a new domain. Unlike existing approaches, we propose lightweight yet effective methods for performing domain adaptation for neural models. Specifically, we introduce adaptation layers on top of existing neural architectures, where no re-training using the source domain data is required. We conduct extensive empirical studies and show that our approach significantly outperforms state-of-the-art methods.
arXiv comment11 pages, accepted as a long paper in EMNLP 2018
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Exploiting Similarities among Languages for Machine Translation
- Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks
- How Transferable are Neural Networks in NLP Applications?
- Transfer Learning for Named-Entity Recognition with Neural Networks
- A Simple Regularization-based Algorithm for Learning Cross-Domain Word Embeddings
- Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning