EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphs

TL;DR

EventGround is a framework that grounds free-text narratives to structured eventuality-centric knowledge graphs, improving narrative reasoning with interpretability and state-of-the-art performance.

Contribution

It introduces a comprehensive approach to grounding narratives to knowledge graphs, addressing event representation and sparsity issues, and demonstrating superior reasoning performance.

Findings

Outperforms baseline models with GNN or LLM-based reasoning.

Achieves state-of-the-art results in narrative reasoning tasks.

Provides interpretable evidence through grounded knowledge.

Abstract

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.