Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning
This addresses the challenge of improving NER in scenarios lacking document contexts, though it is incremental as it builds on existing retrieval and learning methods.
The paper tackles the problem of Named Entity Recognition (NER) when document-level contexts are unavailable by retrieving external contexts via a search engine and using Cooperative Learning to align representations. The result is state-of-the-art performance on 8 NER datasets across 5 domains.
Recent advances in Named Entity Recognition (NER) show that document-level contexts can significantly improve model performance. In many application scenarios, however, such contexts are not available. In this paper, we propose to find external contexts of a sentence by retrieving and selecting a set of semantically relevant texts through a search engine, with the original sentence as the query. We find empirically that the contextual representations computed on the retrieval-based input view, constructed through the concatenation of a sentence and its external contexts, can achieve significantly improved performance compared to the original input view based only on the sentence. Furthermore, we can improve the model performance of both input views by Cooperative Learning, a training method that encourages the two input views to produce similar contextual representations or output label distributions. Experiments show that our approach can achieve new state-of-the-art performance on 8 NER data sets across 5 domains.