Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training

Proceedings of the 28th International Conference on Computational Linguistics, pages 5799–5809 Barcelona, Spain (Online), December 8-13, 2020 5799 Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training Yingyao Wang1∗, Junwei Bao2, Guangyi Liu3, Youzheng Wu2, Xiaodong He2, Bowen Zhou2, Tiejun Zhao1 1Harbin Institute of Technology, Harbin, China 2JD AI Research, Beijing, China 3The Chinese University of Hong Kong, Shenzhen, China {baojunwei,wuyouzheng1,xiaodong.he,bowen.zhou}@jd.com yywang@hit-mtlab.net,gy-liu@foxmail.com,tjzhao@hit.edu.cn Abstract This paper aims to enhance the few-shot relation classification especially for sentences that jointly describe multiple relations. Due to the fact that some relations usually keep high co- occurrence in the same context, previous few-shot relation classifiers struggle to distinguish them with few annotated instances. To alleviate the above relation confusion problem, we propose CTEG, a model equipped with two mechanisms to learn to decouple these easily-confused re- lations. On the one hand, an Entity-Guided Attention (EGA) mechanism, which leverages the syntactic relations and relative positions between each word and the specified entity pair, is in- troduced to guide the attention to filter out information causing confusion. On the other hand, a Confusion-Aware Training (CAT) method is proposed to explicitly learn to distinguish relations by playing a pushing-away game between classifying a sentence into a true relation and its con- fusing relation. Extensive experiments are conducted on the FewRel dataset, and the results show that our proposed model achieves comparable and even much better results to strong baselines in terms of accuracy. Furthermore, the ablation test and case study verify the effectiveness of our proposed EGA and CAT, especially in addressing the relation confusion problem. 1 Introduction Relation classification (RC) aims to identify the relation between two specified entities in a sentence. Previous supervised approaches on this task heavily depend on human-annotated data, which limit their performance on classifying the relations with insufficient instances. Therefore, making the RC models capable of identifying relations with few training instances becomes a crucial challenge. Inspired by the success of few-shot learning methods in the computer vision community (Vinyals et al., 2016; Sung et al., 2017; Santoro et al., 2016) and some other natural language processing tasks (Chen et al., 2016; Qin et al., 2020; Zhou et al., 2019), Han et al. (2018) first introduce the few-shot learning to RC task and propose the FewRel dataset. Recently, many works focus on this task and achieve remarkable performance (Gao et al., 2019a; Snell et al., 2017; Ye and Ling, 2019). Previous few-shot relation classifiers perform well on sentences with only one relation of a single entity pair. However, in real natural language, a sentence usually jointly describes multiple relations of different entity pairs. Since these relations usually keep high co-occurrence in the same context, previous few-shot RC models struggle to distinguish them with few annotated instances. For example, Table 1 shows three instances from the FewRel dataset, where each sentence describes multiple relations with corresponding keyphrases highlighted (colored) as evidence. When specified two entities (bold black) in the sentence, there is a great opportunity for the instance to …

Content truncated to 500 words