Title: Leveraging knowledge graph for domain-specific Chinese named entity recognition via lexicon-based relational graph transformer

Authors: Yunbo Gao; Guanghong Gong; Bipeng Ye; Xingyu Tian; Ni Li; Haitao Yuan

Addresses: School of Automation Science and Electrical Engineering, Beihang University, China ' School of Automation Science and Electrical Engineering, Beihang University, China ' School of Automation Science and Electrical Engineering, Beihang University, China ' School of Automation Science and Electrical Engineering, Beihang University, China ' School of Automation Science and Electrical Engineering, Beihang University, China ' School of Automation Science and Electrical Engineering, Beihang University, China

Abstract: Leveraging knowledge graphs (KGs) has been an emerging direction to improve the performance of deep learning-based Chinese named entity recognition (CNER). Nevertheless, most existing methods directly inject correlated words into sentences but ignore word boundaries that are crucial for CNER. Conflicts among incorrect word segmentations may misguide models to predict incorrect labels. To solve this problem, this work investigates a novel lexicon-based relational graph transformer (LRGT), which combines relational graph-structured inputs and transformer tailored for lexicon-augmented CNER. In LRGT, characters and self-matched lexicon words are fully interacted through a two-phase relational graph softmax message passing mechanism. The finally enhanced character representation in LRGT dynamically integrates both lexical and relative positional information, which is distinguishable for the identification. Results on four benchmark datasets demonstrate that LRGT significantly outperforms several state-of-the-art methods. We further demonstrate that LRGT with KG achieves higher performance on two public specific-domain CNER datasets. LRGT performs up to 3.35 times faster than several typical baselines while achieving better F1-score by up to 1.92% and 2.24%, respectively.

Keywords: deep learning; knowledge graph; Chinese named entity recognition; CNER; lexicon augmentation; relational graph transformer; RGT; lexicon-based relational graph transformer; LRGT.

DOI: 10.1504/IJBIC.2023.131912

International Journal of Bio-Inspired Computation, 2023 Vol.21 No.3, pp.148 - 162

Received: 15 Dec 2022
Accepted: 15 Mar 2023
Published online: 04 Jul 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article