Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification

Proceedings of the 28th International Conference on Computational Linguistics, pages 2967–2978 Barcelona, Spain (Online), December 8-13, 2020 2967 Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification Juan Li1,2∗, Ruoxu Wang1,2∗, Ningyu Zhang1,2∗†, Wen Zhang1,2, Fan Yang1,2, Huajun Chen1,2 † 1 Zhejiang University 2 AZFT Joint Lab for Knowledge Engine {lijuan18,ruoxuwang,zhangningyu,wenzhang2015,21821249,huajunsir}@zju.edu.cn Abstract Relation classification aims to extract semantic relations between entity pairs from the sentences. However, most existing methods can only identify seen relation classes that occurred during training. To recognize unseen relations at test time, we explore the problem of zero-shot relation classification. Previous work regards the problem as reading comprehension or textual entail- ment, which have to rely on artificial descriptive information to improve the understandability of relation types. Thus, rich semantic knowledge of the relation labels is ignored. In this paper, we propose a novel logic-guided semantic representation learning model for zero-shot relation classification. Our approach builds connections between seen and unseen relations via implicit and explicit semantic representations with knowledge graph embeddings and logic rules. Exten- sive experimental results demonstrate that our method can generalize to unseen relation types and achieve promising improvements. 1 Introduction Relation Classification (RC) is an important task in information extraction, aiming to extract the relation between two given entities based on their related context. RC has attracted increasing attention due to its broad applications in many downstream tasks, such as knowledge base construction (Luan et al., 2018) and question answering (Yu et al., 2017). Conventional supervised RC approaches can not satisfy the practical needs of the relation classifica- tion. In the real world, there exist massive amounts of fine-grained relations. And, the labeled relation types are limited, and each type usually has a certain number of labeled samples. Naturally, it is pro- hibitive to generalize to new (unseen) relations (i.e., the model will fail when predicting a type with no training examples). For example, in Figure 1, basin country is an unseen relation type with no labeled sentence in the training stage. To this end, it is urgent for models to be able to extract relations in a zero-shot scenario. Previous zero-shot relation classification (ZSRC) approaches leverage transfer learning procedures by reading comprehension (Levy et al., 2017), textual entailment (Obamuyide and Vlachos, 2018), and so on. However, those methods have to rely on artificial descriptive information to improve the understand- ability of relation types. Inspired by the zero-shot learning in computer vision (Palatucci et al., 2009), it is natural to learn a mapping from the feature space of input samples to the semantic space such as class labels through a projection function. The hypothesis is to build the semantic connections between seen and unseen relations. Conventional approaches usually leverage word embeddings (Mikolov et al., 2013) of labels as a common semantic space. We argue that for relation classification, rich semantic knowledge is neglected in the relation labels space: Implicit Semantic Connection with Knowledge Graph Embedding. Previous studies (Yang et al., 2014) have shown that the Knowledge Graph Embeddings (KGEs) of semantically similar …

Content truncated to 500 words