Rethinking the Value of Gazetteer in Chinese Named Entity Recognition

TL;DR

This paper systematically analyzes the impact of gazetteers on Chinese NER, revealing their benefits, limitations, and guiding principles for constructing effective gazetteers to improve model performance.

Contribution

It provides a comprehensive evaluation of gazetteer-enhanced NER models, offering insights into their effectiveness and guidelines for building better gazetteers.

Findings

Gazetteers improve detection in difficult datasets.

High-quality pre-trained lexeme embeddings significantly boost performance.

Effective gazetteers should cover entities present in both training and testing sets.

Abstract

Gazetteer is widely used in Chinese named entity recognition (NER) to enhance span boundary detection and type classification. However, to further understand the generalizability and effectiveness of gazetteers, the NLP community still lacks a systematic analysis of the gazetteer-enhanced NER model. In this paper, we first re-examine the effectiveness several common practices of the gazetteer-enhanced NER models and carry out a series of detailed analysis to evaluate the relationship between the model performance and the gazetteer characteristics, which can guide us to build a more suitable gazetteer. The findings of this paper are as follows: (1) the gazetteer improves most of the situations that the traditional NER model datasets are difficult to learn. (2) the performance of model greatly benefits from the high-quality pre-trained lexeme embeddings. (3) a good gazetteer should cover more entities that can be matched in both the training set and testing set.