Learning Reasoning Patterns for Relational Triple Extraction with Mutual Generation of Text and Graph

Abstract

Relational triple extraction is a critical task for constructing knowledge graphs. Existing methods focused on learning text patterns from explicit relational mentions. However, they usually suffered from ignoring relational reasoning patterns, thus failed to extract the implicitly implied triples. Fortunately, the graph structure of a sentence's relational triples can help find multi-hop reasoning paths. Moreover, the type inference logic through the paths can be captured with the sentence's supplementary relational expressions that represent the real-world conceptual meanings of the paths' composite relations. In this paper, we propose a unified framework to learn the relational reasoning patterns for this task. To identify multi-hop reasoning paths, we construct a relational graph from the sentence (text-tograph generation) and apply multi-layer graph convolutions to it. To capture the relation type inference logic of the paths, we propose to understand the unlabeled conceptual expressions by reconstructing the sentence from the relational graph (graph-to-text generation) in a self-supervised manner. Experimental results on several benchmark datasets demonstrate the effectiveness of our method. * Equal contribution.George is Judy's father and David's grandfather.

Automatic Table Union Search with Tabular Representation Learning

“…Self-supervised learning (SSL) is a method for building models where the output labels are already included in the input data, eliminating the need for additional labeled data (Liu et al, 2021;Hu et al, 2021a,b;Liu et al, 2022d,c). SSL has been widely used in NLP domains such as sentence generation (West et al, 2019;Yan et al, 2021), document processing (You et al, 2021;Ginzburg et al, 2021), natural language inference (Li et al, , 2023, and text reasoning (Klein and Nabi, 2020;Fu et al, 2020;Chen et al, 2022). BERT (Devlin et al, 2019) is one of the most eminent SSL methods which exploit self-supervisions from corpus with next sentence prediction and masked language modeling tasks.…”

Sequence Generation with Label Augmentation for Relation Extraction

“…Previous efforts mainly focus on the following three aspects. The first one designs novel modules or model architectures, for example, Chen, Zhang, and Huang (2022) proposes a framework of text and graph to learn relational reasoning patterns for relational triple extraction. The second one utilizes various external datasets or resources to enrich the input (Cabot and Navigli 2021;Zhang et al 2022a;Paolini et al 2021;Lu et al 2022).…”