A Relation-Oriented Clustering Method for Open Relation Extraction
This work addresses a specific bottleneck in unsupervised relation discovery for natural language processing, offering an incremental improvement over existing clustering-based methods.
The paper tackles the problem in open relation extraction where high-dimensional vectors cause clusters to misalign with relational semantics, proposing a relation-oriented clustering model that reduces error rates by 29.2% and 15.7% on two datasets compared to state-of-the-art methods.
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 to form a cluster structure, so that the learned 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.