A Reinforcement Learning Framework for N-Ary Document-Level Relation Extraction

Knowledge Bases (KBs) have become more complex because some facts in KBs include more than two entities. The construction and completion of these KBs require a new relation extraction task to retrieve complex facts from the text. To address this issue, we present a new N-ary Document-Level relation extraction task that involves extracting relations that 1) include an arbitrary number of entities, and 2) can span multiple sentences within a document. This new task requires inferring relation labels and entity completeness, i.e., whether the entities in the document are (insufficient to describe the relation. We propose a reinforcement learning-based relation classifier training framework that can adapt most existing binary document-level relation extractors to this task. Extensive experimental evaluation demonstrates that our proposed framework is effective in reducing the impact of noise introduced by distant supervision or unrelated sentences in the document.