Abstract
Distantly supervised relation extraction (DSRE) generates large-scale annotated data by aligning unstructured text with knowledge bases. However, automatic construction methods cause a substantial number of incorrect annotations, thereby introducing noise into the training process. Most sentence-level relation extraction methods rely on filters to remove noise instances, meanwhile, they ignore some useful information in negative instances. To effectively reduce noise interference, we propose a Multi-teacher Knowledge Distillation framework for Relation Extraction (MKDRE) to extract semantic relations from noisy data based on both global information and local information. MKDRE addresses two main problems: the deviation in knowledge propagation of a single teacher and the limitation of traditional distillation temperature on information utilization. Specifically, we utilize flexible temperature regulation (FTR) to adjust the temperature assigned to each training instance, so as to dynamically capture local relations between instances. Furthermore, we introduce information entropy of hidden layers to gain stable temperature calculations. Finally, we propose multi-view knowledge distillation (MVKD) to express global relations among teachers from various perspectives to gain more reliable knowledge. The experimental results on NYT19-1.0 and NYT19-2.0 datasets show that our proposed MKDRE significantly outperforms previous methods in sentence-level relation extraction.
Supported by the National Natural Science Foundation of China under the Grant No. 62172451, and supported by Open Research Projects of Zhejiang Lab under the Grant No. 2022KG0AB01.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wu, S., He, Y.: Enriching pre-trained language model with entity information for relation classification. In: CIKM, pp. 2361–2364 (2019)
Wei, Z., Su, J., Wang, Y., Tian, Y., Chang, Y.: A novel cascade binary tagging framework for relational triple extraction. In: ACL, pp. 1476–1488 (2020)
Mintz, M., Bills, S., Snow, R., Jurafsky, D.: Distant supervision for relation extraction without labeled data. In: ACL, pp. 1003–1011 (2009)
Zeng, D., Liu, K., Chen, Y., Zhao, J.: Distant supervision for relation extraction via piecewise convolutional neural networks. In: EMNLP, pp. 1753–1762 (2015)
Lin, Y., Shen, S., Liu, Z., Luan, H., Sun, M.: Neural relation extraction with selective attention over instances. In: ACL, pp. 2124–2133 (2016)
Vashishth, S., Joshi, R., Prayaga, S.S., Bhattacharyya, C., Talukdar, P.: RESIDE: improving distantly-supervised neural relation extraction using side information. In: EMNLP, pp. 1257–1266 (2018)
Lin, X., Liu, T., Jia, W., Gong, Z.: Distantly supervised relation extraction using multi-layer revision network and confidence based multi-instance learning. In: EMNLP, pp. 165–174 (2021)
Feng, J., Huang, M., Zhao, L., Yang, Y., Zhu, X.: Reinforcement learning for relation classification from noisy data. In: AAAI (2018)
Zeng, X., He, S., Liu, K.: Large scaled relation extraction with reinforcement learning. In: AAAI (2018)
He, Z., Chen, W., Wang, Y., Zhang, W., Wang, G., Zhang, M.: Improving neural relation extraction with positive and unlabeled learning. In: AAAI, pp. 7927–7934 (2020)
Ma, R., Gui, T., Li, L., Zhang, Q., Huang, X., Zhou, Y.:SENT: sentence-level distant relation extraction via negative training. In: ACL, pp. 6201–6213 (2021)
Li, R., Yang, C., Li, T., Su, S.: MidTD: a simple and effective distillation framework for distantly supervised relation extraction. ACM Trans. Inf. Syst. (TOIS) 40(4), 1–32 (2022)
Zhang, Z., et al.: Distilling knowledge from well-informed soft labels for neural relation extraction. In: AAAI, pp. 9620–9627 (2020)
Riedel, S., Yao, L., McCallum, A.: Modeling relations and their mentions without labeled text. In: Balcázar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010. LNCS (LNAI), vol. 6323, pp. 148–163. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15939-8_10
Wang, X., Yang, J., Wang, Q., Su, C.: Threat intelligence relationship extraction based on distant supervision and reinforcement learning. In: SEKE, pp. 572–576 (2020)
Qin, P., Xu, W., Wang, W. Y.: DSGAN: generative adversarial training for distant supervision relation extraction. In: ACL, pp. 496–505 (2018)
Li, Y., et al.: Self-attention enhanced selective gate with entity-aware embedding for distantly supervised relation extraction. In: AAAI, pp. 8269–8276 (2020)
Du, J., Han, J., Way, A., Wan, D.: Multi-level structured self-attentions for distantly supervised relation extraction. In: EMNLP, pp. 2216–2225 (2018)
Wang, J., Liu, Q.: Distant supervised relation extraction with position feature attention and selective bag attention. Neurocomputing 461, 552–561 (2021)
Chen, T., Shi, H., Tang, S., Chen, Z., Wu, F., Zhuang, Y.: CIL: contrastive instance learning framework for distantly supervised relation extraction. In: ACL, pp. 6191–6200 (2021)
Li, D., Zhang, T., Hu, N., Wang, C., He, X.: HiCLRE: a hierarchical contrastive learning framework for distantly supervised relation extraction. In: ACL, pp. 2567–2578 (2022)
Zhang, Y., Fei, H., Li, P.: ReadsRE: retrieval-augmented distantly supervised relation extraction. In: ACM SIGIR, pp. 2257–2262 (2021)
Peng, T., Han, R., Cui, H., Yue, L., Han, J., Liu, L.: Distantly supervised relation extraction using global hierarchy embeddings and local probability constraints. Knowl.-Based Syst. 235, 107637 (2022)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NeurIPS (2015)
Li, Y., Yang, J., Song, Y., Cao, L., Luo, J., Li, L. J.: Learning from noisy labels with distillation. In: ICCV, pp. 1910–1918 (2017)
Sarfraz, F., Arani, E., Zonooz, B.: Knowledge distillation beyond model compression. In: ICPR, pp. 6136–6143 (2021)
Zhou, H., et al.: Rethinking soft labels for knowledge distillation: a bias-variance tradeoff perspective. In: ICLR (2021)
Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: CVPR, pp. 7130–7138 (2017)
Lei, K., et al.: Cooperative denoising for distantly supervised relation extraction. In: COLING, pp. 426–436 (2018)
Zhang, S., Zheng, D., Hu, X., Yang, M.: Bidirectional long short-term memory networks for relation classification. In: PACLIC, pp. 73–78 (2015)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, pp. 4171–4186 (2019)
Liu, Y., et al.: RoBERTa: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Ren, X., et al.: Cotype: joint extraction of typed entities and relations with knowledge bases. In: WWW, pp. 1015–1024 (2017)
Jia, W., Dai, D., Xiao, X., Wu, H.: ARNOR: attention regularization based noise reduction for distant supervision relation classification. In: ACL, pp. 1399–1408 (2019)
Zhou, P., et al.: Attention-based bidirectional long short-term memory networks for relation classification. In: ACL, pp. 207–212 (2016)
Qin, P., Xu, W., Wang, W. Y.: Robust distant supervision relation extraction via deep reinforcement learning. In: ACL, pp. 2137–2147 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Fei, H., Tan, Y., Huang, W., Long, J., Huang, J., Yang, L. (2024). A Multi-teacher Knowledge Distillation Framework for Distantly Supervised Relation Extraction with Flexible Temperature. In: Song, X., Feng, R., Chen, Y., Li, J., Min, G. (eds) Web and Big Data. APWeb-WAIM 2023. Lecture Notes in Computer Science, vol 14332. Springer, Singapore. https://doi.org/10.1007/978-981-97-2390-4_8
Download citation
DOI: https://doi.org/10.1007/978-981-97-2390-4_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2389-8
Online ISBN: 978-981-97-2390-4
eBook Packages: Computer ScienceComputer Science (R0)