Low-Resource Named Entity Recognition Based on Multi-hop Dependency Trigger

TL;DR

This paper introduces an automatic trigger annotation method using syntactic parsing to improve low-resource NER, demonstrating comparable results to manual trigger labeling on English datasets.

Contribution

It proposes a novel automatic trigger annotation approach for low-resource NER using syntactic parsing, reducing manual effort and maintaining competitive performance.

Findings

Comparable performance to manual trigger-based models

Effective in low-resource NER scenarios

Validated on CONLL 2003 and BC5CDR datasets

Abstract

This paper presents a simple and effective approach in low-resource named entity recognition (NER) based on multi-hop dependency trigger. Dependency trigger refer to salient nodes relative to a entity in the dependency graph of a context sentence. Our main observation is that there often exists trigger which play an important role to recognize the location and type of entity in sentence. Previous research has used manual labelling of trigger. Our main contribution is to propose use a syntactic parser to automatically annotate trigger. Experiments on two English datasets (CONLL 2003 and BC5CDR) show that the proposed method is comparable to the previous trigger-based NER model.