Abstract
The methods of Chinese relation extraction(CRE) based on the neural network can be divided into two categories according to the input mode(word-based and character-based). The performance of word-based models depends on the accuracy of word segmentation. Unfortunately, there are still errors in existing word segmentation tools (methods). Among the character-based models, Lattice LSTM-based models have been successful in CRE. However, such RNN-based models cannot meet the requirements of parallel computing and thus have natural drawbacks in model training and inference. There is much word polysemy in Chinese that constrains the performance of CRE. Most CRE models are built on English datasets, which often perform poorly on Chinese datasets. To address the above issues, we propose a method for CRE with the Polysemy Rethinking Mechanism. In this method, (1) we use a CNN-based architecture in which input is characters. It can incorporate word-level information through the lexicon to correct the error caused by word segmentation. (2) We propose a Polysemy Rethinking Mechanism, which can alleviate the problems caused by multiple meanings of one word by adding multiple sense information to the model. (3) Compared with the Lattice LSTM-based model, our model improves computational efficiency to gain results. We conduct experiments on two real-world datasets of CRE. The results show that our method achieves better performance than the state-of-the-art ones.
Similar content being viewed by others
References
Liu C, Sun W, Chao W et al (2013) Convolution neural network for relation extraction. In: The 13th IEEE international conference on data mining(ICDM), pp 231–242
Zeng D, Liu K, Lai S, Zhou G et al (2014) Relation classification via convolutional deep neural network. In: Proceedings of COLING, pp 2335–2344
Zeng D, Liu K, Chen Y et al (2015) Distant supervision for relation extraction via piecewise convolutional neural networks. In: Proceedings of EMNLP, pp 1753–1762
Lin K, Shen S, Liu Z et al (2016) Neural relation extraction with selective attention over instances. In: ACL, vol 1, pp 2124–2133
Sun Y, Wang S, Li Y et al (2019) Ernie: Enhanced representation through knowledge integration. arXiv:1904.09223
Peters M, Neumann M, Logan R et al (2019) Knowledge enhanced contextual word representations. In: EMNLP, pp 43–54
Wang R, Tang D, Duan N et al (2020) K-Adapter: Infusing knowledge into pre-trained models with adapters. arXiv:2002.01808
Joshi M, Chen D, Liu Y et al (2020) Span BERT: Improving pre-training by representing and predicting spans. In: Transactions of the association for computational linguistics, vol 8, pp 64–77
Li Z, Ding N, Liu Z et al (2019) Chinese relation extraction with multi-grained information and external linguistic knowledge. In: ACL, pp 4377–4386
Carlson A, Betteridge J, Kisiel B et al (2010) Toward an architecture for never-ending language learning. In: Proceedings of AAAI, pp 1306–1313
Wang M (2008) A re-examination of dependency path kernels for relation extraction. In: IJCNLP, pp 841–846
Huang Y, Wang W (2017) Deep residual learning for weakly-supervised relation extraction. In: EMNLP, pp 1803–1807
Zhou P, Shi W, Tian J et al (2016) Attention-based bidirectional long short-term memory networks for relation classification. In: ACL, pp 207–212
Lee J, Seo S, Choi Y (2019) Semantic relation classification via bidirectional LSTM networks with entity-aware attention using latent entity typing. In: Symmetry, vol 11, pp 785–790
Yamada I, Asai A, Shindo H et al (2020) LUKE: Deep contextualized entity representations with entityaware self-attention. In: EMNLP, pp 6442–6454
Qin Y, Yang W, Wang K et al (2021) Entity relation extraction based on entity indicators. In: Symmetry, vol 13, pp 539–544
Dong Z, Dong Q (2003) Hownet-a hybrid language and knowledge resource. In: proceedings of NLP-KE
Qi F, Yang C, Liu Z et al (2019) Openhownet: An open sememe-based lexical knowledge base. arXiv:1901.09957
Li X, Jie Z, Feng J et al (2017) Learning with rethinking: Recurrently improving convolutional neural networks through feedback. Pattern Recognition, p 79
Gui T, Ma R, Zhang Q et al (2019) CNN-Based Chinese NER with Lexicon Rethinking. In: IJCAI, pp 4982–4988
Lan Z, Chen M, Goodman S et al (2020) ALBERT: A lite BERT for self-supervised learning of language representations. In: ICLR
Niu Y, Xie R, Liu Z et al (2017) Improved word representation learning with sememes. In: ACL, pp 2049–2058
Chen Q, Ling Z, Zhu X (2018) Enhancing sentence embedding with generalized pooling. In: COLING, pp 1815–1826
Xu J, Wen J, Sun X et al (2017) A discourse-level named entity recognition and relation extraction dataset for chinese literature text. arXiv:1711.07010
Mikolov T, Sutskever I, Chen K et al (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, pp 3111–3119
Kingma DP, Ba J (2014) Adam: A Method for Stochastic Optimization. arXiv:1412.6980
Shen Y, Huang X (2016) Attention-Based Convolutional Neural Network for Semantic relation extraction. In: COLING, pp 2526–2536
Zhou P, Shi W, Tian J et al (2016) Attention-based bidirectional long short-term memory networks for relation classification. In: ACL, pp 207–212
Eberts M, Ulges A (2019) Span-based joint entity and relation extraction with transformer pre-training. arXiv:1909.07755
Sun Y, Wang S, Li Y et al (2019) ERNIE:, Enhanced representation through knowledge integration. arXiv:1904.09223
Cui Y, Che W, Liu T, et al. (2021) Pre-training with whole word masking for chinese BERT. In: IEEE trans. audio speech lang. process, vol 29, pp 3504–3514
Cui Y, Che W, Liu T et al (2020) Revisiting pre-trained models for chinese natural language processing. In: EMNLP(Findings), pp 657–668
Zhou W, Chen M (2021) An improved baseline for sentence-level relation extraction. arXiv:2102.01373
Zhong Z, Chen D (2020) A frustratingly easy approach for entity and relation extraction. In: NAACL, pp 50–61
Wen J, Sun X, Ren X et al (2018) Structure regularized neural network for entity relation classification for chinese literature text. In: NAACL, pp 365–370
Zeng X, Zhong J, Wang C et al (2021) Chinese relation extraction with flat-lattice encoding and pretrain-transfer strategy. In: KSEM, pp 30–40
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
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
Zhao, Q., Gao, T. & Guo, N. A novel chinese relation extraction method using polysemy rethinking mechanism. Appl Intell 53, 7665–7676 (2023). https://doi.org/10.1007/s10489-022-03817-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03817-5