Chinese Word Segmentation with Heterogeneous Graph Neural Network
Not on the map. Why?
Abstract (arXiv)
In recent years, deep learning has achieved significant success in the Chinese word segmentation (CWS) task. Most of these methods improve the performance of CWS by leveraging external information, e.g., words, sub-words, syntax. However, existing approaches fail to effectively integrate the multi-level linguistic information and also ignore the structural feature of the external information. Therefore, in this paper, we proposed a framework to improve CWS, named HGNSeg. It exploits multi-level external information sufficiently with the pre-trained language model and heterogeneous graph neural network. The experimental results on six benchmark datasets (e.g., Bakeoff 2005, Bakeoff 2008) validate that our approach can effectively improve the performance of Chinese word segmentation. Importantly, in cross-domain scenarios, our method also shows a strong ability to alleviate the out-of-vocabulary (OOV) problem.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 20 of its 49 references that are in the map. First posted on arXiv 22 Jan 2022.
Builds on
20 of 49 references.
References · 20
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
- 2016Conditional Image Generation with PixelCNN Decoderscited by 862
- 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
- 2016Language Modeling with Gated Convolutional Networkscited by 702
- 2018Graph Convolutional Networks for Text Classificationcited by 345
- 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137
- 2017Graph Convolutional Encoders for Syntax-aware Neural Machine Translationcited by 70
- 2019Text Level Graph Neural Network for Text Classificationcited by 60
- 2021Lexicon Enhanced Chinese Sequence Labeling Using BERT Adaptercited by 34
- 2017Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRFcited by 16
8 more
- 2019Toward Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learningcited by 11
- 2017Neural Word Segmentation with Rich Pretrainingcited by 10
- 2018State-of-the-art Chinese Word Segmentation with Bi-LSTMscited by 10
- 2017Adversarial Multi-Criteria Learning for Chinese Word Segmentationcited by 7
- 2020Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentationcited by 6
- 2018Neural Chinese Word Segmentation with Dictionary Knowledgecited by 4
- 2017Effective Neural Solution for Multi-Criteria Word Segmentationcited by 2
- 2019Improving Cross-Domain Chinese Word Segmentation with Word Embeddingscited by 2
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.