Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

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.

PDF Abstract ACL 2021 PDF ACL 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Named Entity Recognition (NER) BC5CDR CL-L2 F1 90.99 # 3
Named Entity Recognition (NER) CMeEE BERT-CRF (Replicated in AdaSeq) F1 68.97 # 1
Named Entity Recognition (NER) CoNLL++ CL-KL F1 94.81 # 2
Chunking CoNLL 2000 BERT-CRF (Replicated in AdaSeq) Exact Span F1 97.18 # 2
Named Entity Recognition (NER) CoNLL 2003 (English) CL-KL F1 93.85 # 7
Named Entity Recognition (NER) CoNLL 2003 (English) BERT-CRF (Replicated in AdaSeq) F1 93.35 # 22
Chinese Named Entity Recognition MSRA BERT-CRF (Replicated in AdaSeq) F1 96.69 # 2
Named Entity Recognition (NER) NCBI-disease CL-KL F1 88.96 # 10
Chinese Named Entity Recognition Resume NER BERT-CRF (Replicated in AdaSeq) F1 96.87 # 1
Chinese Named Entity Recognition Weibo NER BERT-CRF (Replicated in AdaSeq) F1 72.77 # 1
Named Entity Recognition (NER) WNUT 2016 CL-KL F1 58.98 # 2
Named Entity Recognition (NER) WNUT 2017 BERT-CRF (Replicated in AdaSeq) F1 59.69 # 2
Named Entity Recognition (NER) WNUT 2017 CL-KL F1 60.45 # 1

Methods