A Hierarchical Framework for Relation Extraction with Reinforcement Learning
This addresses relation extraction for natural language processing applications, representing an incremental improvement through a novel hierarchical approach to handle overlapping relations.
The paper tackles the problem of relation extraction where existing methods don't fully model interactions between relation types and entity mentions, by proposing a hierarchical reinforcement learning framework that decomposes extraction into relation detection and entity extraction policies. Results show it achieves better performance than existing methods and is more powerful for extracting overlapping relations on public distantly supervised datasets.
Most existing methods determine relation types only after all the entities have been recognized, thus the interaction between relation types and entity mentions is not fully modeled. This paper presents a novel paradigm to deal with relation extraction by regarding the related entities as the arguments of a relation. We apply a hierarchical reinforcement learning (HRL) framework in this paradigm to enhance the interaction between entity mentions and relation types. The whole extraction process is decomposed into a hierarchy of two-level RL policies for relation detection and entity extraction respectively, so that it is more feasible and natural to deal with overlapping relations. Our model was evaluated on public datasets collected via distant supervision, and results show that it gains better performance than existing methods and is more powerful for extracting overlapping relations.