ToHRE: A Top-Down Classification Strategy with Hierarchical Bag Representation for Distantly Supervised Relation Extraction

Proceedings of the 28th International Conference on Computational Linguistics, pages 1665–1676 Barcelona, Spain (Online), December 8-13, 2020 1665 ToHRE: A Top-Down Classification Strategy with Hierarchical Bag Representation for Distantly Supervised Relation Extraction Erxin Yu1,2, Wenjuan Han5, Yuan Tian1,2,4∗, Yi Chang1,2,3∗ 1School of Artificial Intelligence, Jilin University 2Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University 3International Center of Future Science, Jilin University 4College of Biological and Agricultural Engineering, Jilin University 5Department of Computer Science, National University of Singapore yuex19@mails.jlu.edu.cn, dcshanw@nus.edu.sg, yuantian@jlu.edu.cn, yichang@jlu.edu.cn Abstract Distantly Supervised Relation Extraction (DSRE) has proven to be effective to find relational facts from texts, but it still suffers from two main problems: the wrong labeling problem and the long-tail problem. Most of the existing approaches address these two problems through flat clas- sification, which lacks hierarchical information of relations. To leverage the informative relation hierarchies, we formulate DSRE as a hierarchical classification task and propose a novel hierar- chical classification framework, which extracts the relation in a top-down manner. Specifically, in our proposed framework, 1) we use a hierarchically-refined representation method to achieve hierarchy-specific representation; 2) a top-down classification strategy is introduced instead of training a set of local classifiers. The experiments on NYT dataset demonstrate that our approach significantly outperforms other state-of-the-art approaches, especially for the long-tail problem. 1 Introduction Knowledge bases (KBs) such as Freebase (Bollacker et al., 2008), DBpedia (Auer et al., 2007), and NELL (Carlson et al., 2010) currently play an essential role in NLP tasks including information retrieval and question answering. As current KBs are still far from complete compared with the infinite real-world facts, relation extraction (RE) which aims to extract relations between two entities in texts and enrich KBs has attracted a surge of research interest. Most existing supervised RE methods require high quality labeled data, which is time-consuming and labor-intensive. Therefore, Mintz et al. (2009) propose the distant supervision (DS) approach to automatically generate a large amount of training data for RE by aligning KBs with large-scale unlabeled corpora. Two problems have to be addressed in building an efficient DS model. The main problem, namely the wrong labeling problem, comes from the assumption of DS. DS is based on an assumption: if two entities have a relation in KBs, all sentences that contain these two entities will express this relation. This strong and unrealistic assumption inevitably bring some noise. For example, DS method may mistakenly label the sentence “Steve Jobs passed away the day before Apple unveiled iPhone 4s in late 2011” with the relation business/company/founders. Secondly, although DS method can automatically generate large-scale training data, this training data can only cover a limited part of relations. Nearly 70% of the relations are long-tail and still suffer from data deficiency in the widely used New York Times (NYT) dataset. To alleviate the wrong labeling problem, Riedel et al. (2010) and Hoffmann et al. (2011) propose the multi-instance learning (MIL) framework, which assigns a label to a bag of sentences containing a common entity pair. Based on …

Content truncated to 500 words