Abstract
Chinese named entity recognition (CNER) is one of the fundamental tasks in natural language processing (NLP), supporting a wide range of downstream NLP tasks for Chinese texts. The recent best-performing CNER works have extensively shown that by using external knowledge, such as lexicons and syntactic dependency features, considerable task improvements can be secured. Nevertheless, we note that current works still fail to sufficiently integrate rich external knowledge to boost the CNER performances further. In this work, we propose to enhance the CNER by incorporating heterogeneous knowledge from the linguistic, syntactic and semantic perspectives. For linguistic source, we consider (1) part-of-speech (POS) tags and (2) multi-granularity lexicons, including characters, words and subwords. For syntactic source, we adopt label-wise character-level syntactic dependency structures. For semantic source, we employ (1) BERT contextualized representations and (2) rich sememe representations from HowNet. We build heterogeneous graphs based on the multi-granularity lexicons and encode them with graph attention neural network (GAT). We also propose an innovative label-aware graph convolutional network (LGCN) for modeling the syntactic dependency arcs and labels simultaneously. Further, we present a sememe composition attention module for better injecting the sememe representations. Our system achieves new state-of-the-art CNER performances over current best baselines on four benchmark datasets. Further in-depth analysis has been conducted to reveal the contribution of each used resource, as well as the strengths of our proposed methods for the task improvements.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data availability
We will make all the data and material publicly available upon the acceptance of our work.
Code availability
We will make all the codes publicly available upon the acceptance of our work.
References
Bikel DM, Miller S, Schwartz R, Weischedel R (1997) Nymble: a highperformance learning name-finder. In: Proceedings of the conference on applied natural language processing
Bunescu R, Mooney R (2005) A shortest path dependency kernel for relation extraction. In: Proceedings of human language technology conference and conference on empirical methods in natural language processing, pp 724–731
Cao P, Chen Y, Liu K, Zhao J, Liu S (2018) Adversarial transfer learning for Chinese named entity recognition with self-attention mechanism. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 182–192
Che W, Wang M, Manning CD, Liu T (2013) Named entity recognition with bilingual constraints. In: Proceedings of the 2013 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 52–62
Chen A, Peng F, Shan R, Sun G (2006) Chinese named entity recognition with conditional probabilistic models. In: Proceedings of the SIGHAN workshop on Chinese language processing, pp 173–176
Chen Y, Xu L, Liu K, Zeng D, Zhao J (2015) Event extraction via dynamic multi-pooling convolutional neural networks. In: Proceedings of the annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing, pp 167–176
Collobert R, Weston J, Bottou L, Karlen M, Kavukcuoglu K, Kuksa PP (2011) Natural language processing (almost) from scratch. J Mach Learn Res 12:2493–2537
Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics, pp 4171–4186
Diefenbach D, López V, Singh KD, Maret P (2018) Core techniques of question answering systems over knowledge bases: a survey. Knowl Inf Syst 55(3):529–569
Dong C, Zhang J, Zong C, Hattori M, Di H (2016) Character-based LSTM-CRF with radical-level features for Chinese named entity recognition. In: Proceedings of the conference on natural language processing and Chinese computing, pp 239–250
Dozat T, Manning CD (2017) Deep biaffine attention for neural dependency parsing. In: Proceedings of the international conference on learning representations
Fei H, Guo Y, Li B, Ji D, Ren Y (2021) Adversarial shared-private model for cross-domain clinical text entailment recognition. Knowledge-Based Syst 221:106962
Fei H, Ji D, Li B, Liu Y, Ren Y, Li F (2021) Rethinking boundaries: End-to-end recognition of discontinuous mentions with pointer networks. In: Proceedings of the AAAI conference on artificial intelligence, pp 12785–12793
Fei H, Li F, Li B, Ji D (2021) Encoder-decoder based unified semantic role labeling with label-aware syntax. In: Proceedings of the AAAI conference on artificial intelligence, pp 12794–12802
Fei H, Ren Y, Ji D (2020) Improving text understanding via deep syntax-semantics communication. In: Proceedings of the conference on empirical methods in natural language processing, pp 84–93
Fei H, Ren Y, Ji D (2020) Mimic and conquer: Heterogeneous tree structure distillation for syntactic NLP. Findings of the association for computational linguistics: EMNLP 2020:183–193
Fei H, Ren Y, Ji D (2020) Retrofitting structure-aware transformer language model for end tasks. In: Proceedings of the 2020 conference on empirical methods in natural language processing(EMNLP), pp 2151–2161
Fei H, Ren Y, Wu S, Li B, Ji D (2021) Latent target-opinion as prior for document-level sentiment classification: a variational approach from fine-grained perspective. In: Proceedings of the WWW: the web conference, pp 553–564
Fei H, Ren Y, Zhang Y, Ji D, Liang X (2020) Enriching contextualized language model from knowledge graph for biomedical information extraction. Brief Bioinform
Fei H, Wu S, Ren Y, Li F, Ji D (2021) Better combine them together! integrating syntactic constituency and dependency representations for semantic role labeling. In: Findings of the association for computational linguistics: ACL/IJCNLP 2021, pp 549–559
Fei H, Zhang M, Ji D (2020) Cross-lingual semantic role labeling with high-quality translated training corpus. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 7014–7026
Fei H, Zhang M, Li B, Ji D (2021) End-to-end semantic role labeling with neural transition-based model. In: Proceedings of the AAAI conference on artificial intelligence, pp 12803–12811
Fei H, Zhang M, Li F, Ji D (2020) Cross-lingual semantic role labeling with model transfer. IEEE/ACM Trans Audio Speech Lang Process 28:2427–2437
Fei H, Zhang Y, Ren Y, Ji D (2020) Latent emotion memory for multi-label emotion classification. In: Proceedings of the AAAI conference on artificial intelligence, pp 7692–7699
Gilmer J, Schoenholz SS, Riley PF, Vinyals O, Dahl GE (2017) Neural message passing for quantum chemistry. In: Proceedings of the international conference on machine learning, pp 1263–1272
Gui T, Zou Y, Zhang Q, Peng M, Fu J, Wei Z, Huang X (2019) A lexicon-based graph neural network for Chinese NER. In: Proceedings of the conference on empirical methods in natural language processing, pp 1040–1050
He H, Sun X (2017) F-score driven max margin neural network for named entity recognition in Chinese social media. In: Proceedings of the 15th conference of the European chapter of the association for computational linguistics, pp 713–718
He J, Wang H (2008) Chinese named entity recognition and word segmentation based on character. In: Proceedings of the SIGHAN Workshop on Chinese language processing
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Huang S, Sun X, Wang H (2017) Addressing domain adaptation for Chinese word segmentation with global recurrent structure. In: Proceedings of the international joint conference on natural language processing, pp 184–193
Isozaki H, Kazawa H (2002) Efficient support vector classifiers for named entity recognition. In: Proceedings of the international conference on computational linguistics
Jie Z, Lu W (2019) Dependency-guided LSTM-CRF for named entity recognition. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, pp 3862–3872
Jie Z, Muis AO, Lu W (2017) Efficient dependency-guided named entity recognition. In: Singh SP, Markovitch S (eds) Proceedings of the association for the advancement of artificial intelligence, pp 3457–3465
Kim Y (2014) Convolutional neural networks for sentence classification. In: Proceedings of the 2014 conference on empirical methods in natural language processing, pp 1746–1751
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proceedings of the international conference on learning representations
Lafferty JD, McCallum A, Pereira FCN (2001) Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the international conference on machine learning, pp 282–289
Lample G, Ballesteros M, Subramanian S, Kawakami K, Dyer C (2016) Neural architectures for named entity recognition. In: Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 260–270
Levow GA (2006) The third international Chinese language processing bakeoff: Word segmentation and named entity recognition. In: Proceedings of the SIGHAN workshop on Chinese language processing, pp 108–117
Li B, Fei H, Ren Y, Ji D (2020) Nominal compound chain extraction: a new task for semantic-enriched lexical chain. In: Proceedings of the natural language processing and Chinese computing, pp 119–131
Li Z, Ding N, Liu Z, Zheng H, Shen Y (2019) Chinese relation extraction with multi-grained information and external linguistic knowledge. In: Proceedings of the annual meeting of the association for computational linguistics, pp 4377–4386
Liu J, Huang M, Zhu X (2010) Recognizing biomedical named entities using skip-chain conditional random fields. In: Proceedings of the workshop on biomedical natural language processing, pp 10–18
Liu L, Shang J, Ren X, Xu FF, Gui H, Peng J, Han J (2018) Empower sequence labeling with task-aware neural language model. In: Proceedings of the association for the advancement of artificial intelligence, pp 5253–5260
Liu Z, Zhu C, Zhao T (2010) Chinese named entity recognition with a sequence labeling approach: Based on characters, or based on words? In: Proceedings of the advanced intelligent computing theories and applications, pp 634–640
Lu Y, Zhang Y, Ji D (2016) Multi-prototype Chinese character embedding. In: Proceedings of the tenth international conference on language resources and evaluation
Ma X, Hovy E (2016) End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF. In: Proceedings of the annual meeting of the association for computational linguistics, pp 1064–1074
Marcheggiani D, Titov I (2017) Encoding sentences with graph convolutional networks for semantic role labeling. In: Proceedings of the conference on empirical methods in natural language processing, pp 1506–1515
Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Proceedings of the 27th annual conference on neural information orocessing systems, pp 3111–3119
Niu Y, Xie R, Liu Z, Sun M (2017) Improved word representation learning with Sememes. In: Proceedings of the annual meeting of the association for computational linguistics, pp 2049–2058
Passos A, Kumar V, McCallum A (2014) Lexicon infused phrase embeddings for named entity resolution. In: Proceedings of the conference on computational natural language learning, pp 78–86
Peng N, Dredze M (2015) Named entity recognition for Chinese social media with jointly trained embeddings. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp 548–554
Provilkov I, Emelianenko D, Voita E (2020) BPE-dropout: Simple and effective subword regularization. In: Proceedings of the annual meeting of the association for computational linguistics, pp 1882–1892
Qi F, Huang J, Yang C, Liu Z, Chen X, Liu Q, Sun M (2019) Modeling semantic compositionality with sememe knowledge. In: Proceedings of the annual meeting of the association for computational linguistics, pp 5706–5715
Sasano R, Kurohashi S (2008) Japanese named entity recognition using structural natural language processing. In: Proceedings of the international joint conference on natural language processing
Sui D, Chen Y, Liu K, Zhao J, Liu S (2019) Leverage lexical knowledge for Chinese named entity recognition via collaborative graph network. In: Proceedings of the 2019 conference on empirical methods in natural language processing, pp 3830–3840
Tang Z, Wan B, Yang L (2020) Word-character graph convolution network for Chinese named entity recognition. IEEE/ACM Trans Audio Speech Lang Process 28:1520–1532
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Proceedings of the international conference on neural information processing, pp 5998–6008
Velickovic P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y (2018) Graph attention networks. In: Proceedings of the 6th international conference on learning representations
Wang M, Che W, Manning CD (2013) Effective bilingual constraints for semi-supervised learning of named entity recognizers. In: Proceedings of the association for the advancement of artificial intelligence
Weischedel R, Palmer M, Marcus M, Hovy E, Pradhan S, Ramshaw L, Xue N, Taylor A, Kaufman J, Franchini M, El-Bachouti M, Belvin R, Houston A (2011) Ontonotes release 4.0. LDC2011T03, Philadelphia, Penn.: Linguistic Data Consortium
Wu S, Fei H, Ren Y, Li B, Li F, Ji D (2021) High-order pair-wise aspect and opinion terms extraction with edge-enhanced syntactic graph convolution. IEEE/ACM Trans Audio Speech Lang Process 29:2396–2406
Xue N, Shen L (2003) Chinese word segmentation as LMR tagging. In: Proceedings of the second SIGHAN workshop on Chinese language processing, pp 176–179
Yang J, Teng Z, Zhang M, Zhang Y (2016) Combining discrete and neural features for sequence labeling. In: Proceedings of the computational linguistics and intelligent text processing, pp 140–154. Springer
Zhang C, Li Q, Song D (2019) Aspect-based sentiment classification with aspect-specific graph convolutional networks. In: Proceedings of the 2019 conference on empirical methods in natural language processing, pp 4568–4578
Zhang S, Qin Y, Wen J, Wang X (2006) Word segmentation and named entity recognition for SIGHAN bakeoff3. In: Proceedings of the SIGHAN workshop on Chinese language processing, pp 158–161
Zhang Y, Yang J (2018) Chinese NER using lattice LSTM. In: Proceedings of the annual meeting of the association for computational linguistics, pp 1554–1564
Zhendong Dong QD (2003) Hownet—a hybrid language and knowledge resource. In: Proceedings of the natural language processing and knowledge engineering
Zhou J, Qu W, Zhang F (2013) Chinese named entity recognition via joint identification and categorization. Chin J Electron 22(2):225–230
Zhu Y, Wang G (2019) CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 3384–3393
Funding
This work is supported by the science and technology research project of Jiang Xi Education Department under Grant Nos. GJJ201340, GJJ201302, GJJ201338, GJJ201341, the teaching reform research project of Jingdezhen Ceramic Institute under Grant No. TDJG-2020-02, the Key Research and Development Plan of Jiang Xi province under Grant No. 20202BBEL53020, and the College Student Innovation and Entrepreneurship Training Program under Grant Nos. 202110408027, S202110408067, S202110408107X, the Open Fund Project of Jiangxi Province Earthquake Prevention and Mitigation and Engineering Geological Disaster Detection Engineering Research Center under Grant No. SDGD202110, the Science and Technology project of Jingdezhen under Grant No. 20202GYZD013-001.
Author information
Authors and Affiliations
Contributions
YN was conducting most of the experiments, and most of the article writing. YZ was responsible for part of the majority of the idea, as well as part of the writing and providing computational resources. YP was partially providing the idea, and conducting some of the experiments, e.g., data processing, analysis experiments, offering important suggestions. LY was conducting part of the experiments, and performing proofreading.
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare that there are no conflicts of interest regarding the publication of this paper.
Consent to participate
All authors have agreed the consent to participate in the work.
Consent for publication
All authors have checked the manuscript and have agreed to the publication.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Nie, Y., Zhang, Y., Peng, Y. et al. Borrowing wisdom from world: modeling rich external knowledge for Chinese named entity recognition. Neural Comput & Applic 34, 4905–4922 (2022). https://doi.org/10.1007/s00521-021-06680-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06680-6