Dependency-driven Relation Extraction with Attentive Graph Convolutional Networks

Dependency-driven Relation Extraction with Attentive Graph Convolutional Networks Yuanhe Tian♥⇤, Guimin Chen}⇤, Yan Song♠~†, Xiang Wan~ ♥University of Washington }QTrade ♠The Chinese University of Hong Kong (Shenzhen) ~Shenzhen Research Institute of Big Data ♥yhtian@uw.edu }chenguimin@foxmail.com ♠songyan@cuhk.edu.cn ~wanxiang@sribd.cn Abstract Syntactic information, especially dependency trees, has been widely used by existing stud- ies to improve relation extraction with better semantic guidance for analyzing the context information associated with the given entities. However, most existing studies suffer from the noise in the dependency trees, especially when they are automatically generated, so that in- tensively leveraging dependency information may introduce confusions to relation classifi- cation and necessary pruning is of great impor- tance in this task. In this paper, we propose a dependency-driven approach for relation ex- traction with attentive graph convolutional net- works (A-GCN). In this approach, an atten- tion mechanism upon graph convolutional net- works is applied to different contextual words in the dependency tree obtained from an off- the-shelf dependency parser, to distinguish the importance of different word dependencies. Consider that dependency types among words also contain important contextual guidance, which is potentially helpful for relation extrac- tion, we also include the type information in A-GCN modeling. Experimental results on two English benchmark datasets demonstrate the effectiveness of our A-GCN, which outper- forms previous studies and achieves state-of- the-art performance on both datasets.1 1 Introduction Relation extraction (RE), which aims to detect the relationship between entity mentions from raw text, is one of the most important tasks in information extraction and retrieval, and plays a crucial role in supporting many downstream natural language processing (NLP) applications such as text mining (Distiawan et al., 2019), sentiment analysis (Sun *Equal contribution. †Corresponding author. 1The code and models involved in this paper are released at https://github.com/cuhksz-nlp/RE-AGCN. Figure 1: An illustration of noises in the dependency tree that can hurt relation extraction, where the word dependency connected in between “pumpkin mixture” and “bowl” (whose relation is content-container) may introduce confusion to the system when the object is to predict the relation between “milk” and “pumpkin mixture” (whose relation is entity-destination). et al., 2019), question answering (Xu et al., 2016a), and summarization (Wang and Cardie, 2012). Recently, neural RE methods (Zeng et al., 2014; Zhang and Wang, 2015; Xu et al., 2015; dos Santos et al., 2015; Zhang et al., 2015; Wang et al., 2016; Zhou et al., 2016; Zhang et al., 2017) with powerful encoders (such as CNN, RNN, and Transformers) have significantly improved model performance for RE without requiring any elaborately designed systems or manually constructed features. These methods are superior in capturing contextual in- formation and thus enable RE systems to better understand the text and identify relations between entities in the given text. Adopting neural models to help RE is not only straightforward and effec- tive, but is also expected to incorporate more di- verse and informative knowledge into RE systems. Among all different knowledge sources, syntactic information, especially the dependency trees, have been demonstrated to be beneficial in many stud- ies …

Content truncated to 500 words