Discontinuous Named Entity Recognition as Maximal Clique Discovery

06/01/2021
by   Yucheng Wang, et al.
0

Named entity recognition (NER) remains challenging when entity mentions can be discontinuous. Existing methods break the recognition process into several sequential steps. In training, they predict conditioned on the golden intermediate results, while at inference relying on the model output of the previous steps, which introduces exposure bias. To solve this problem, we first construct a segment graph for each sentence, in which each node denotes a segment (a continuous entity on its own, or a part of discontinuous entities), and an edge links two nodes that belong to the same entity. The nodes and edges can be generated respectively in one stage with a grid tagging scheme and learned jointly using a novel architecture named Mac. Then discontinuous NER can be reformulated as a non-parametric process of discovering maximal cliques in the graph and concatenating the spans in each clique. Experiments on three benchmarks show that our method outperforms the state-of-the-art (SOTA) results, with up to 3.5 percentage points improvement on F1, and achieves 5x speedup over the SOTA model.

READ FULL TEXT
research
06/28/2021

A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition

Research on overlapped and discontinuous named entity recognition (NER) ...
research
03/20/2023

Multi-task Transformer with Relation-attention and Type-attention for Named Entity Recognition

Named entity recognition (NER) is an important research problem in natur...
research
12/30/2016

PAMPO: using pattern matching and pos-tagging for effective Named Entities recognition in Portuguese

This paper deals with the entity extraction task (named entity recogniti...
research
04/28/2020

An Effective Transition-based Model for Discontinuous NER

Unlike widely used Named Entity Recognition (NER) data sets in generic d...
research
12/19/2021

Unified Named Entity Recognition as Word-Word Relation Classification

So far, named entity recognition (NER) has been involved with three majo...
research
09/28/2017

Graph Convolutional Networks for Named Entity Recognition

In this paper we investigate the role of the dependency tree in a named ...
research
11/02/2018

Bayesian Ensembles of Crowds and Deep Learners for Sequence Tagging

Current methods for sequence tagging, a core task in NLP, are data hungr...

Please sign up or login with your details

Forgot password? Click here to reset