Rethinking the Value of Gazetteer in Chinese Named Entity Recognition
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 35 references that are in the map. First posted on arXiv 6 Jul 2022.
Builds on
18 of 35 references.
References · 18
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
- 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
- 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
- 2018Chinese NER Using Lattice LSTMcited by 81
- 2020FLAT: Chinese NER Using Flat-Lattice Transformercited by 67
- 2018Analogical Reasoning on Chinese Morphological and Semantic Relationscited by 50
- 2019Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learningcited by 46
- 2020Rethinking Generalization of Neural Models: A Named Entity Recognition Case Studycited by 35
- 2020Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoningcited by 33
6 more
- 2020Soft Gazetteers for Low-Resource Named Entity Recognitioncited by 20
- 2020Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sourcescited by 14
- 2017Neural Word Segmentation with Rich Pretrainingcited by 10
- 2020Self-Attention Gazetteer Embeddings for Named-Entity Recognitioncited by 5
- 2019Chinese Named Entity Recognition Augmented with Lexicon Memorycited by 1
- 2020Incorporating Uncertain Segmentation Information into Chinese NER for Social Media Textcited by 1
Built on by
Citing papers per year: 2023: 1.
1 paper.