# Simplify the Usage of Lexicon in Chinese NER

arXiv: https://arxiv.org/abs/1908.05969 · HTML: https://mlsanity.com/paper/1908.05969/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2019.

## Built on by (most cited first, 23 of 23)

- [Unified Named Entity Recognition as Word-Word Relation Classification](https://mlsanity.com/paper/2112.10070/) (2021)
- [Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter](https://mlsanity.com/paper/2105.07148/) (2021)
- [Boundary Smoothing for Named Entity Recognition](https://mlsanity.com/paper/2204.12031/) (2022)
- [MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition](https://mlsanity.com/paper/2107.05418/) (2021)
- [PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasets](https://mlsanity.com/paper/2211.14838/) (2022)
- [Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity Recognition](https://mlsanity.com/paper/2204.05544/) (2022)
- [Masked Conditional Random Fields for Sequence Labeling](https://mlsanity.com/paper/2103.10682/) (2021)
- [PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition](https://mlsanity.com/paper/2402.04838/) (2024)
- [DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling](https://mlsanity.com/paper/2109.08818/) (2021)
- [Deep Span Representations for Named Entity Recognition](https://mlsanity.com/paper/2210.04182/) (2022)
- [TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities](https://mlsanity.com/paper/2407.21693/) (2024)
- [Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting](https://mlsanity.com/paper/2204.11406/) (2022)
- [MarkBERT: Marking Word Boundaries Improves Chinese BERT](https://mlsanity.com/paper/2203.06378/) (2022)
- [Qtrade AI at SemEval-2022 Task 11: An Unified Framework for Multilingual NER Task](https://mlsanity.com/paper/2204.07459/) (2022)
- [A Unified Framework of Medical Information Annotation and Extraction for Chinese Clinical Text](https://mlsanity.com/paper/2203.03823/) (2022)
- [Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction](https://mlsanity.com/paper/2303.05082/) (2023)
- [Using Domain Knowledge for Low Resource Named Entity Recognition](https://mlsanity.com/paper/2203.14738/) (2022)
- [NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition](https://mlsanity.com/paper/2205.05832/) (2022)
- [Exploiting Word Semantics to Enrich Character Representations of Chinese Pre-trained Models](https://mlsanity.com/paper/2207.05928/) (2022)
- [Application of Data Encryption in Chinese Named Entity Recognition](https://mlsanity.com/paper/2208.14627/) (2022)
- [Improving Chinese Named Entity Recognition by Search Engine Augmentation](https://mlsanity.com/paper/2210.12662/) (2022)
- [Research on Named Entity Recognition in Improved transformer with R-Drop structure](https://mlsanity.com/paper/2306.08315/) (2023)
- [CRENER: A Character Relation Enhanced Chinese NER Model](https://mlsanity.com/paper/2412.10858/) (2024)

## Abstract (arXiv)

Recently, many works have tried to augment the performance of Chinese named entity recognition (NER) using word lexicons. As a representative, Lattice-LSTM (Zhang and Yang, 2018) has achieved new benchmark results on several public Chinese NER datasets. However, Lattice-LSTM has a complex model architecture. This limits its application in many industrial areas where real-time NER responses are needed. In this work, we propose a simple but effective method for incorporating the word lexicon into the character representations. This method avoids designing a complicated sequence modeling architecture, and for any neural NER model, it requires only subtle adjustment of the character representation layer to introduce the lexicon information. Experimental studies on four benchmark Chinese NER datasets show that our method achieves an inference speed up to 6.15 times faster than those of state-ofthe-art methods, along with a better performance. The experimental results also show that the proposed method can be easily incorporated with pre-trained models like BERT.