Multi-Grained Named Entity Recognition

This paper presents a novel framework, MGNER, for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be non-overlapping or totally nested. Different from traditional approaches regarding NER as a sequential labeling task and annotate entities consecutively, MGNER detects and recognizes entities on multiple granularities: it is able to recognize named entities without explicitly assuming non-overlapping or totally nested structures. MGNER consists of a Detector that examines all possible word segments and a Classifier that categorizes entities. In addition, contextual information and a self-attention mechanism are utilized throughout the framework to improve the NER performance. Experimental results show that MGNER outperforms current state-of-the-art baselines up to 4.4% in terms of the F1 score among nested/non-overlapping NER tasks.

PDF Abstract ACL 2019 PDF ACL 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Nested Named Entity Recognition ACE 2004 MGNER F1 79.5 # 21
Named Entity Recognition (NER) ACE 2004 MGNER F1 79.5 # 7
Multi-Task Supervision n # 1
Nested Mention Recognition ACE 2004 MGNER F1 79.5 # 5
Nested Mention Recognition ACE 2005 MGNER F1 78.2 # 5
Nested Named Entity Recognition ACE 2005 MGNER F1 78.2 # 19
Named Entity Recognition (NER) ACE 2005 MGNER F1 78.2 # 15
Named Entity Recognition (NER) CoNLL 2003 (English) MGNER F1 92.28 # 43

Methods


No methods listed for this paper. Add relevant methods here