From Discourse to Narrative: Knowledge Projection for Event Relation Extraction
This addresses the problem of building comprehensive event knowledge graphs for natural language processing applications, representing an incremental improvement through a novel hybrid method.
The paper tackles the problem of limited coverage in event-centric knowledge graphs due to sparse connectives and lack of labeled data by proposing a knowledge projection paradigm that projects discourse knowledge to narratives, reducing data requirements and extracting implicit event relations. Experimental results show MKPNet achieves state-of-the-art performance and verifies the value of extracted relations.
Current event-centric knowledge graphs highly rely on explicit connectives to mine relations between events. Unfortunately, due to the sparsity of connectives, these methods severely undermine the coverage of EventKGs. The lack of high-quality labelled corpora further exacerbates that problem. In this paper, we propose a knowledge projection paradigm for event relation extraction: projecting discourse knowledge to narratives by exploiting the commonalities between them. Specifically, we propose Multi-tier Knowledge Projection Network (MKPNet), which can leverage multi-tier discourse knowledge effectively for event relation extraction. In this way, the labelled data requirement is significantly reduced, and implicit event relations can be effectively extracted. Intrinsic experimental results show that MKPNet achieves the new state-of-the-art performance, and extrinsic experimental results verify the value of the extracted event relations.