Jointly Extracting Explicit and Implicit Relational Triples with Reasoning Pattern Enhanced Binary Pointer Network

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5694–5703 June 6–11, 2021. ©2021 Association for Computational Linguistics 5694 Jointly Extracting Explicit and Implicit Relational Triples with Reasoning Pattern Enhanced Binary Pointer Network Yubo Chen†, Yunqi Zhang†, Changran Hu‡, Yongfeng Huang† †Department of Electronic Engineering & BNRist, Tsinghua University, Beijing, China ‡University of California, Berkeley, USA ybch14@gmail.com changran_hu@berkeley.eduzhang-yq15@outlook.com yfhuang@tsinghua.edu.cn Abstract Relational triple extraction is a crucial task for knowledge graph construction. Existing methods mainly focused on explicit relational triples that are directly expressed, but usually suffer from ignoring implicit triples that lack explicit expressions. This will lead to serious incompleteness of the constructed knowledge graphs. Fortunately, other triples in the sen- tence provide supplementary information for discovering entity pairs that may have implicit relations. Also, the relation types between the implicitly connected entity pairs can be iden- tified with relational reasoning patterns in the real world. In this paper, we propose a uni- fied framework to jointly extract explicit and implicit relational triples. To explore entity pairs that may be implicitly connected by rela- tions, we propose a binary pointer network to extract overlapping relational triples relevant to each word sequentially and retain the infor- mation of previously extracted triples in an ex- ternal memory. To infer the relation types of implicit relational triples, we propose to intro- duce real-world relational reasoning patterns in our model and capture these patterns with a relation network. We conduct experiments on several benchmark datasets, and the results prove the validity of our method. 1 Introduction Relational triple extraction is defined as automat- ically recognizing semantic relations with triple structures (subject, relation, object) among multi- ple entities in a sentence. It is a critical task for constructing Knowledge Graphs (KGs) from unla- beled corpus (Dong et al., 2014). Early work of relational triple extraction ap- plied pipeline methods (Zelenko et al., 2003; Chan and Roth, 2011), which ran entity recognition and relation classification separately. However, such pipeline approaches suffered from error propaga- tion. To address this issue, recent work proposed to jointly extract entity and relations from the text Work for Live in Locate in … Mark Spencer, a designer of Digium, a company in Huntsville … Person Organization Location Explict Triple Implicit Triple Figure 1: An example of explicit and implicit relational triples. Italic phrases are key relational expressions cor- responding to the explicit relational triples. with feature-based methods (Yu and Lam, 2010; Li and Ji, 2014; Ren et al., 2017). Afterward, neural network-based models were proposed to eliminate hand-crafted features (Gupta et al., 2016; Zheng et al., 2017). More recently, several methods were proposed to extract overlapping triples, such as tagging-based (Dai et al., 2019; Wei et al., 2020), graph-based (Wang et al., 2018; Fu et al., 2019), copy-based (Zeng et al., 2018, 2019, 2020) and token pair linking models (Wang et al., 2020). Existing models achieved considerable success on extracting explicit triples which have direct rela- tional expressions in the …

Content truncated to 500 words