TURNER: The Uncertainty-based Retrieval Framework for Chinese NER

TL;DR

TURNER introduces an uncertainty-based retrieval framework for Chinese NER that leverages auxiliary knowledge sources like search engines, improving accuracy and surpassing previous lexicon-based methods on benchmark datasets.

Contribution

The paper proposes a novel uncertainty sampling and knowledge fusion approach for Chinese NER, reducing reliance on domain-specific lexicons and enhancing retrieval efficiency.

Findings

TURNER outperforms existing lexicon-based methods.

Achieves new state-of-the-art results on four benchmark datasets.

Effective in handling ambiguous and OOV entities.

Abstract

Chinese NER is a difficult undertaking due to the ambiguity of Chinese characters and the absence of word boundaries. Previous work on Chinese NER focus on lexicon-based methods to introduce boundary information and reduce out-of-vocabulary (OOV) cases during prediction. However, it is expensive to obtain and dynamically maintain high-quality lexicons in specific domains, which motivates us to utilize more general knowledge resources, e.g., search engines. In this paper, we propose TURNER: The Uncertainty-based Retrieval framework for Chinese NER. The idea behind TURNER is to imitate human behavior: we frequently retrieve auxiliary knowledge as assistance when encountering an unknown or uncertain entity. To improve the efficiency and effectiveness of retrieval, we first propose two types of uncertainty sampling methods for selecting the most ambiguous entity-level uncertain components of the input text. Then, the Knowledge Fusion Model re-predict the uncertain samples by combining retrieved knowledge. Experiments on four benchmark datasets demonstrate TURNER's effectiveness. TURNER outperforms existing lexicon-based approaches and achieves the new SOTA.