EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphs
This addresses the challenge of interpretable narrative reasoning for AI systems by explicitly leveraging structured knowledge, though it is incremental as it builds on existing eventuality-centric KGs.
The paper tackles the problem of grounding free-texts to eventuality-centric knowledge graphs for narrative reasoning, and the proposed EventGround framework achieves state-of-the-art performance by outperforming baseline models when combined with GNN or LLM-based graph reasoning models.
Narrative reasoning relies on the understanding of eventualities in story contexts, which requires a wealth of background world knowledge. To help machines leverage such knowledge, existing solutions can be categorized into two groups. Some focus on implicitly modeling eventuality knowledge by pretraining language models (LMs) with eventuality-aware objectives. However, this approach breaks down knowledge structures and lacks interpretability. Others explicitly collect world knowledge of eventualities into structured eventuality-centric knowledge graphs (KGs). However, existing research on leveraging these knowledge sources for free-texts is limited. In this work, we propose an initial comprehensive framework called EventGround, which aims to tackle the problem of grounding free-texts to eventuality-centric KGs for contextualized narrative reasoning. We identify two critical problems in this direction: the event representation and sparsity problems. We provide simple yet effective parsing and partial information extraction methods to tackle these problems. Experimental results demonstrate that our approach consistently outperforms baseline models when combined with graph neural network (GNN) or large language model (LLM) based graph reasoning models. Our framework, incorporating grounded knowledge, achieves state-of-the-art performance while providing interpretable evidence.