Enhancing Narrative Commonsense Reasoning With Multilevel Causal Knowledge

Narratives is an account of the unfolding of events, along with explanations of how and why these processes and events came to be. To understand narratives, causality has been proven to be especially useful. Causality manifests itself primarily at both the event and sentence levels, offering essential insights into understanding narratives. However, previous works utilize either sentence-level or event-level causalities. In this article, we devise a two-stage approach to fully exploit both levels of causal relationships. In the first stage, by devising posttraining tasks, we inject sentence-level causalities into pretrained language models (PLMs). The causal-enhanced PLMs, which carry sentence-level causalities, can be transferred to downstream tasks. In the second stage, we utilize event causalities to further refine narrative commonsense reasoning. But, the event sparsity problem brings about the difficulty to learn event representations and capture useful causal semantics. To alleviate this problem, we break down events into multiple word components, enabling the retrieval of word-word relations between these components. And it is possible to alleviate the event sparsity problem since word-word relations capture the interplays between event components. Based on the event-level causalities and the word-level relations, we construct the hierarchical knowledge graph (KG) as knowledge ground. A KG-based reasoning process is then employed for narrative commonsense reasoning. Experimental results affirm the effectiveness of our framework.