Abstract
Open relation extraction aims at extracting novel relations from open-domain corpora. However, most recent works typically treat entities and tokens equally while encoding sentences, without taking full advantage of the guiding role of entities in representation learning. In this work, we propose the Entity-Aware Relation Representation learning framework for open relation extraction and establish the new state-of-the-art on standard benchmarks. It gives more attention to entities when learning representations by leveraging an entity-aware attention mechanism. And we further propose a pair-wise contrastive loss to learn relation representations effectively in terms of alignment and uniformity. Extensive experimental results show that our framework achieves significant improvements compared to state-of-the-art models.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The FewRel benchmark provides a training set with 64 relations, a validation set with 16 relations, and a hidden test set with 20 relations which are only for evaluation on https://thunlp.github.io/1/fewrel1.html.
- 2.
- 3.
References
Bagga, A., Baldwin, B.: Entity-based cross-document coreferencing using the vector space model. In: COLING-ACL (1998)
Banko, M., Cafarella, M.J., Soderland, S., Broadhead, M., Etzioni, O.: Open information extraction from the web (2008)
Banko, M., Etzioni, O.: The tradeoffs between open and traditional relation extraction. In: ACL (2008)
Blondel, V., Guillaume, J.L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks. J. Stat. Mech. Theory Exp. 2008, 10008 (2008)
Bordes, A., Usunier, N., García-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: NIPS (2013)
Cugmas, M., Ferligoj, A.: On comparing partitions. International Federation of Classification Societies (2015)
Cui, L., Wei, F., Zhou, M.: Neural open information extraction (2018)
Elsahar, H., Demidova, E., Gottschalk, S., Gravier, C., Laforest, F.: Unsupervised open relation extraction. In: Blomqvist, E., Hose, K., Paulheim, H., Ławrynowicz, A., Ciravegna, F., Hartig, O. (eds.) ESWC 2017. LNCS, vol. 10577, pp. 12–16. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-70407-4_3
Han, X., et al.: FewRel: a large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation. ArXiv abs/1810.10147 (2018)
Hu, X., Wen, L., Xu, Y., Zhang, C., Yu, P.S.: SelfORE: self-supervised relational feature learning for open relation extraction. ArXiv abs/2004.02438 (2020)
Ji, G., He, S., Xu, L., Liu, K., Zhao, J.: Knowledge graph embedding via dynamic mapping matrix. In: ACL (2015)
Lin, D., Pantel, P.: Dirt @sbt@discovery of inference rules from text. In: KDD 2001 (2001)
Marcheggiani, D., Titov, I.: Discrete-state variational autoencoders for joint discovery and factorization of relations. Trans. Assoc. Comput. Linguist. 4, 231–244 (2016)
Peng, H., et al.: Learning from context or names? An empirical study on neural relation extraction. In: EMNLP (2020)
Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word representation. In: EMNLP (2014)
Rosenberg, A., Hirschberg, J.: V-measure: a conditional entropy-based external cluster evaluation measure. In: EMNLP-CoNLL (2007)
Simon, É., Guigue, V., Piwowarski, B.: Unsupervised information extraction: regularizing discriminative approaches with relation distribution losses. In: ACL (2019)
Stanovsky, G., Michael, J., Zettlemoyer, L., Dagan, I.: Supervised open information extraction. In: NAACL-HLT (2018)
Tran, T.T., Le, P., Ananiadou, S.: Revisiting unsupervised relation extraction. ArXiv abs/2005.00087 (2020)
Vaswani, A., et al.: Attention is all you need. ArXiv abs/1706.03762 (2017)
Wu, R., et al.: Open relation extraction: Relational knowledge transfer from supervised data to unsupervised data. In: EMNLP/IJCNLP (2019)
Yao, L., Riedel, S., McCallum, A.: Unsupervised relation discovery with sense disambiguation. In: ACL (2012)
Zeng, D., Liu, K., Lai, S., Zhou, G., Zhao, J.: Relation classification via convolutional deep neural network. In: COLING (2014)
Zhang, S., Huang, H., Liu, J., Li, H.: Spelling error correction with soft-masked BERT (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, Z., Zhang, Y., Wang, H., Zhu, J. (2021). Entity-Aware Relation Representation Learning for Open Relation Extraction. In: Wang, L., Feng, Y., Hong, Y., He, R. (eds) Natural Language Processing and Chinese Computing. NLPCC 2021. Lecture Notes in Computer Science(), vol 13028. Springer, Cham. https://doi.org/10.1007/978-3-030-88480-2_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-88480-2_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88479-6
Online ISBN: 978-3-030-88480-2
eBook Packages: Computer ScienceComputer Science (R0)
