Abstract
Entity representation plays a fundamental role in modern relation extraction models. Previous efforts usually explicitly distinguish entities from contextual words, e.g., by introducing position embedding w.r.t. entities or surrounding entities with special tokens. Inspired by this observation, we propose improving relation extraction via a novel entity-level contrastive learning, which contrasts an entity with both other ones and its contextual words in a mini-batch. To generate high-quality negatives for contrast, we equip our entity-level contrastive learning with an innovative Mixup strategy, which interpolates feature representations of negative entities and contextual words to create new diversified negative examples. Extensive experiments on TACRED, TACRED-revisited, and SemEval2010 show that our method delivers robust performance improvements base on a strong relation extraction baseline. Furthermore, we propose a new metric to measure the overall hardness of the negative examples by considering their dissimilarities with the anchor instance as well as their diversities, explaining the superiority of our method in-depth.
Z. Jinglei and L. Bo—Equal Contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alt, C., Gabryszak, A., Hennig, L.: TACRED revisited: a thorough evaluation of the TACRED relation extraction task. In: ACL 2020 (2020)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT 2019 (2019)
Gao, T., Yao, X., Chen, D.: SimCSE: simple contrastive learning of sentence embeddings. CoRR abs/2104.08821 (2021). https://arxiv.org/abs/2104.08821
Gunel, B., Du, J., Conneau, A., Stoyanov, V.: Supervised contrastive learning for pre-trained language model fine-tuning. In: ICLR 2021 (2021)
Guo, Z., Zhang, Y., Lu, W.: Attention guided graph convolutional networks for relation extraction. In: Korhonen, A., Traum, D.R., Màrquez, L. (eds.) ACL 2019 (2009)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: CVPR 2020 (2020)
Hendrickx, I., et al.: SemEval-2010 task 8: multi-way classification of semantic relations between pairs of nominals. In: SemEval@ACL 2010 (2010)
Inoue, H.: Data augmentation by pairing samples for images classification. CoRR abs/1801.02929 (2018). http://arxiv.org/abs/1801.02929
Joshi, M., Chen, D., Liu, Y., Weld, D.S., Zettlemoyer, L., Levy, O.: SpanBERT: improving pre-training by representing and predicting spans. Trans. Assoc. Comput. Linguist. (2020)
Kalantidis, Y., Sariyildiz, M.B., Pion, N., Weinzaepfel, P., Larlus, D.: Hard negative mixing for contrastive learning. In: NeurIPS 2020 (2020)
Khosla, P., et al.: Supervised contrastive learning. In: NeurIPS 2020 (2020)
Li, B., Ye, W., Huang, C., Zhang, S.: Multi-view inference for relation extraction with uncertain knowledge. In: AAAI 2021 (2021)
MacDonald, E., Barbosa, D.: Neural relation extraction on Wikipedia tables for augmenting knowledge graphs. In: CIKM 2020 (2020)
Mandya, A., Bollegala, D., Coenen, F.: Graph convolution over multiple dependency sub-graphs for relation extraction. In: COLING 2020 (2020)
Miwa, M., Bansal, M.: End-to-end relation extraction using LSTMs on sequences and tree structures. In: ACL 2016 (2016)
Pan, X., Wang, M., Wu, L., Li, L.: Contrastive learning for many-to-many multilingual neural machine translation. In: ACL/IJCNLP 2021 (2021)
Peters, M.E., et al.: Knowledge enhanced contextual word representations. In: EMNLP-IJCNLP 2019 (2019)
Qin, Y., et al.: ERICA: improving entity and relation understanding for pre-trained language models via contrastive learning. In: ACL/IJCNLP 2021 (2021)
Ren, F., et al.: Neural relation classification with text descriptions. In: COLING 2018 (2018)
Robinson, J.D., Chuang, C., Sra, S., Jegelka, S.: Contrastive learning with hard negative samples. In: ICLR 2021 (2021)
Soares, L.B., FitzGerald, N., Ling, J., Kwiatkowski, T.: Matching the blanks: distributional similarity for relation learning. In: ACL 2019 (2019)
Su, P., Peng, Y., Vijay-Shanker, K.: Improving BERT model using contrastive learning for biomedical relation extraction. In: BioNLP@NAACL-HLT 2021 (2021)
Tian, Y., Chen, G., Song, Y., Wan, X.: Dependency-driven relation extraction with attentive graph convolutional networks. In: ACL/IJCNLP 2021 (2021)
Xiong, L., et al.: Approximate nearest neighbor negative contrastive learning for dense text retrieval. In: ICLR 2021 (2021)
Xu, P., Barbosa, D.: Connecting language and knowledge with heterogeneous representations for neural relation extraction. In: NAACL-HLT 2019 (2019)
Xue, F., Sun, A., Zhang, H., Chng, E.S.: GDPNet: refining latent multi-view graph for relation extraction. In: AAAI 2021 (2021)
Yamada, I., Asai, A., Shindo, H., Takeda, H., Matsumoto, Y.: LUKE: deep contextualized entity representations with entity-aware self-attention. In: EMNLP 2020 (2020)
Yu, M., Yin, W., Hasan, K.S., dos Santos, C.N., Xiang, B., Zhou, B.: Improved neural relation detection for knowledge base question answering. In: ACL 2017 (2017)
Zeng, D., Liu, K., Lai, S., Zhou, G., Zhao, J.: Relation classification via convolutional deep neural network. In: COLING 2014 (2014)
Zhang, H., Cissé, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: ICLR 2018 (2018)
Zhang, Y., Zhong, V., Chen, D., Angeli, G., Manning, C.D.: Position-aware attention and supervised data improve slot filling. In: EMNLP 2017 (2017)
Zhou, W., Chen, M.: An improved baseline for sentence-level relation extraction. CoRR abs/2102.01373 (2021). https://arxiv.org/abs/2102.01373
Acknowledgment
This work is supported by the Research and Application of Intelligent Regional Industrial Brain Platform.
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
Zhang, J., Li, B., Cao, X., Zhang, M., Zhao, W. (2024). MixCL: Mixed Contrastive Learning for Relation Extraction. In: Yang, DN., Xie, X., Tseng, V.S., Pei, J., Huang, JW., Lin, J.CW. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2024. Lecture Notes in Computer Science(), vol 14648. Springer, Singapore. https://doi.org/10.1007/978-981-97-2238-9_7
Download citation
DOI: https://doi.org/10.1007/978-981-97-2238-9_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2240-2
Online ISBN: 978-981-97-2238-9
eBook Packages: Computer ScienceComputer Science (R0)