Named Entity Recognition as Dependency Parsing

ACL 2020  ·  Juntao Yu, Bernd Bohnet, Massimo Poesio ·

Named Entity Recognition (NER) is a fundamental task in Natural Language Processing, concerned with identifying spans of text expressing references to entities. NER research is often focused on flat entities only (flat NER), ignoring the fact that entity references can be nested, as in [Bank of [China]] (Finkel and Manning, 2009). In this paper, we use ideas from graph-based dependency parsing to provide our model a global view on the input via a biaffine model (Dozat and Manning, 2017). The biaffine model scores pairs of start and end tokens in a sentence which we use to explore all spans, so that the model is able to predict named entities accurately. We show that the model works well for both nested and flat NER through evaluation on 8 corpora and achieving SoTA performance on all of them, with accuracy gains of up to 2.2 percentage points.

PDF Abstract ACL 2020 PDF ACL 2020 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Named Entity Recognition ACE 2004 Biaffine-NER F1 86.7 # 3
Multi-Task Supervision n # 1
Named Entity Recognition ACE 2005 Biaffine-NER F1 85.4 # 6
Named Entity Recognition CoNLL 2002 (Dutch) Biaffine-NER F1 93.7 # 4
Named Entity Recognition CoNLL 2002 (Spanish) Biaffine-NER F1 90.3 # 3
Named Entity Recognition CoNLL 2003 (English) Biaffine-NER F1 93.5 # 12
Named Entity Recognition CoNLL 2003 (German) Biaffine-NER F1 86.4 # 5
Named Entity Recognition CoNLL 2003 (German) Revised Biaffine-NER F1 90.3 # 4
Named Entity Recognition GENIA Biaffine-NER F1 80.5 # 1
Named Entity Recognition Ontonotes v5 (English) Biaffine-NER F1 91.3 # 3

Methods


No methods listed for this paper. Add relevant methods here