A Relation-Oriented Clustering Method for Open Relation Extraction

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9707–9718 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 9707 A Relation-Oriented Clustering Method for Open Relation Extraction Jun Zhao1, Tao Gui2∗, Qi Zhang1∗, Yaqian Zhou1 1School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China 2Institute of Modern Languages and Linguistics, Fudan University {zhaoj19,tgui,qz,zhouyaqian}@fudan.edu.cn Abstract The clustering-based unsupervised relation discovery method has gradually become one of the important methods of open relation extraction (OpenRE). However, high-dimensional vectors can encode complex linguistic information which leads to the problem that the derived clusters cannot explicitly align with the relational semantic classes. In this work, we propose a relation- oriented clustering model and use it to identify the novel relations in the unlabeled data. Specifically, to enable the model to learn to cluster relational data, our method leverages the readily available labeled data of pre-defined relations to learn a relation- oriented representation. We minimize distance between the instance with same relation by gathering the instances towards their corresponding relation centroids form a cluster structure, so that the learnedto representation is cluster-friendly. To reduce the clustering bias on predefined classes, we optimize the model by minimizing a joint objective on both labeled and unlabeled data. Experimental results show that our method reduces the error rate by 29.2% and 15.7%, on two datasets respectively, compared with current SOTA methods. 1 Introduction Relation extraction (RE), a crucial basic task in the field of information extraction, is of the utmost practical interest to various fields including web search (Xiong et al., 2017), knowledge base completion (Bordes et al., 2013), and question answering (Yu et al., 2017). However, conventional RE paradigms such as supervision and distant supervision are generally designed for pre-defined relations, which cannot deal with new emerging relations in the real world. Under this background, open relation extraction (OpenRE) has been widely studied for its use *Corresponding authors. Bill Gates was the CEO of Microsoft Microsoft was founded by Bill Gates Mark Zuckberg, 23, founded Facebook while studing at Harvard Relation Instances e d o c n e r Vector Representation 19.63 26.77 Euclidean Distance Figure 1: Although both instances S2 and S3 express founded relation while S1 expresses CEO relation, the distance between S1 and S2 is still smaller than that between S2 and S3. This is because there may be more similar surface information (e.g. word overlapping) or syntactic structure between S1 and S2, thus the derived clusters cannot explicitly align with relations. in extracting new emerging relational types from open-domain corpora. The approaches used to handle open relations roughly fall into one of two groups. The first group is open information extraction (OpenIE) (Etzioni et al., 2008; Yates et al., 2007; Fader et al., 2011), which directly extracts related phrases as representations of different relational types. However, if not properly canonicalized, the extracted relational facts can be redundant and ambiguous. The second group is unsupervised relation discovery (Yao et al., 2011; Shinyama and Sekine, …

Content truncated to 500 words