Document-level relation extraction using evidence reasoning on RST-GRAPH

Abstract Document-level relation extraction (RE) is a more challenging task providing a new perspective to solve larger and more complex text mining work. Recent document-level RE research following traditional sentence-level methods focus on learning a character representation of one sentence, highlighting the importance of partial words. When applied to a document with a longer text, more entities and more complicated semantics, these traditional methods lacking the ability to select evidence and further reason on them, may not be sufficient to identify all potential relation in the document in an intuitive way. However, some textual semantic associations between entities as well as logical structure of document could provide evidence to the potential relation and explain the reasoning process. Hence, by introducing Rhetorical Structure Theory (RST) as an external knowledge, this article attempts to select appropriate evidence and show reasoning process on a new document-graph, RST-GRAPH, which indicators valid semantic associations between multiple text units through RST and incorporates a set of reasoning modules to capture efficient evidence. Our experimental result shows that the RST-GRAPH, as the first work introducing RST, builds associations in an interpretable manner along discourse relation link between any entities compared to previous graph-oriented models, exhibits a clear process of evidence reasoning with competitive performance on DocRED dataset, and outperforms most existing models on the value of Ign F1.