Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph

Proceedings of the 28th International Conference on Computational Linguistics, pages 2572–2582 Barcelona, Spain (Online), December 8-13, 2020 2572 Modeling Long-distance Node Relations for KBQA with Global Dynamic Graph Xu Wang1, Shuai Zhao1∗, Jiale Han1, Bo Cheng1, Hao Yang2, Jianchang Ao2, Zhenzi Li2 1State Key Laboratory of networking and switching technology, Beijing University of Posts and Telecommunications, Beijing, China 2 2012 Labs, Huawei Technologies CO., LTD, Beijing, China {wxx,zhaoshuaiby,hanjl,chengbo}@bupt.edu.cn , {yanghao30,aojianchang,lizhenzi}@huawei.com , Abstract The structural information of Knowledge Bases (KBs) has proven effective to Question Answer- ing (QA). Previous studies rely on deep graph neural networks (GNNs) to capture rich struc- tural information, which may not model node relations in particularly long distance due to over- smoothing issue. To address this challenge, we propose a novel framework GlobalGraph, which models long-distance node relations from two views: 1) Node type similarity: GlobalGraph as- signs each node a global type label and models long-distance node relations through the global type label similarity; 2) Correlation between nodes and questions: we learn similarity scores be- tween nodes and the question, and model long-distance node relations through the sum score of two nodes. We conduct extensive experiments on two widely used multi-hop KBQA datasets to prove the effectiveness of our method. 1 Introduction Knowledge bases have become critical resources in a variety of natural language processing appli- cations. A KB such as Freebase (Bollacker et al., 2008) always contains millions of facts which are composed of subject-predicate-object triples, also referred to as a relation between two entities. Such rich structural information has proven effective in KB-based Question Answering (KBQA) tasks , which aim to find the answer entities to a factoid question using facts in the targeting KB (Zhou et al., 2018; Zhang et al., 2018). Early studies on KBQA are mainly based on neural network models (Dong et al., 2015; Das et al., 2017), which simulate the similarity between the factoid question and the entities in the KB. Although these methods are effective, the structural information in the KB is not fully utilized, which is essential in the reasoning process (Sun et al., 2018). To address this limitation, recent studies (Sun et al., 2019; Xiong et al., 2019) focus on graph neural networks (GNNs), which update nodes by aggregating their neighbor information in graphs. This updated pattern allows GNNs to capture structural information. However, GNN is a special form of Laplacian smoothing (Li et al., 2018), stacking multiple GNN layers may oversmooth features of nodes and reduce the discriminative power of graph embedding. With this insufficiency, conventional GNNs are poor at modeling long-distance node relations, which is essential for GNN reasoning. (Wu et al., 2019). In this paper, to address the above limitations, we propose a novel framework GlobalGraph, which models long-distance node relations from two views: 1) Modeling node relations by predicting whether two nodes are of the same type label; 2) Modeling node relations by predicting whether two nodes are all correlated with the question. For the 1st view, we assign global type …

Content truncated to 500 words