Multi-view Inference for Relation Extraction with Uncertain Knowledge
This work addresses relation extraction for natural language processing by leveraging uncertain knowledge, representing an incremental improvement over methods using deterministic knowledge graphs.
The paper tackled relation extraction by integrating uncertain knowledge graphs with confidence scores, proposing a multi-view inference framework that combines local context and global knowledge across mention, entity, and concept views, achieving competitive performance on sentence- and document-level tasks.
Knowledge graphs (KGs) are widely used to facilitate relation extraction (RE) tasks. While most previous RE methods focus on leveraging deterministic KGs, uncertain KGs, which assign a confidence score for each relation instance, can provide prior probability distributions of relational facts as valuable external knowledge for RE models. This paper proposes to exploit uncertain knowledge to improve relation extraction. Specifically, we introduce ProBase, an uncertain KG that indicates to what extent a target entity belongs to a concept, into our RE architecture. We then design a novel multi-view inference framework to systematically integrate local context and global knowledge across three views: mention-, entity- and concept-view. The experimental results show that our model achieves competitive performances on both sentence- and document-level relation extraction, which verifies the effectiveness of introducing uncertain knowledge and the multi-view inference framework that we design.