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.

A major challenge for narrative reasoning is to learn narrative coherence.Existing works mainly follow the contrastive learning paradigm.However, the negative samples in their methods can be easily distinguished, which makes their methods unsatisfactory.In this work, we devise two strategies for mining hard negatives, including (1) crisscrossing a narrative and its contrastive variants; and (2) event-level replacement.To obtain contrastive variants, we utilize the Brownian Bridge process to guarantee the quality of generated contrastive narratives.We evaluate our model on several tasks.The result proves the effectiveness of our method, and shows that our method is applicable to many applications.

Counterfactual reasoning in narratives requires predicting how alternative conditions, contrary to what actually happened, might have resulted in different outcomes.One major challenge is to maintain the causality between the counterfactual condition and the generated counterfactual outcome.In this paper, we propose a basic VAE module for counterfactual reasoning in narratives.We further introduce a pre-trained classifier and external event commonsense to mitigate the posterior collapse problem in the VAE approach, and improve the causality between the counterfactual condition and the generated counterfactual outcome.We evaluate our method on two public benchmarks.Experiments show that our method is effective.Code is available at https://github.com/mufeiteng/CausalCRN.

How to generate high-quality textual content is a non-trivial task. Existing methods generally generate text by grounding on word-level knowledge. However, word-level knowledge cannot express multi-word text units, hence existing methods may generate low-quality and unreasonable text. In this paper, we leverage event-level knowledge to enhance text generation. However, event knowledge is very sparse. To solve this problem, we split a coarse-grained event into fine-grained word components to obtain the word-level knowledge among event components. The word-level knowledge models the interaction among event components, which makes it possible to reduce the sparsity of events. Based on the event-level and the word-level knowledge, we devise a multi-level knowledge aware reasoning framework. Specifically, we first utilize event knowledge to make event-based content planning, i.e., select reasonable event sketches conditioned by the input text. Then, we combine the selected event sketches with the word-level knowledge for text generation. We validate our method on two widely used datasets, experimental results demonstrate the effectiveness of our framework to text generation.

This paper focuses on building up distributed representation of words in cause and effect spaces, a task-specific word embedding technique for causality. The causal embedding model is trained on a large set of cause-effect phrase pairs extracted from raw text corpus via a set of high-precision causal patterns. Three strategies are proposed to transfer the positive or negative labels from the level of phrase pairs to the level of word pairs, leading to three causal embedding models (Pairwise-Matching, Max-Matching, and AttentiveMatching) correspondingly. Experimental results have shown that Max-Matching and Attentive-Matching models significantly outperform several state-of-the-art competitors by a large margin on both English and Chinese corpora.

Existing approaches to causal embeddings rely heavily on hand-crafted high-precision causal patterns, leading to limited coverage. To solve this problem, this paper proposes a method to boost causal embeddings by exploring potential verb-mediated causal patterns. It first constructs a seed set of causal word pairs, then uses them as supervision to characterize the causal strengths of extracted verb-mediated patterns, and finally exploits the weighted extractions by those verb-mediated patterns in the construction of boosted causal embeddings. Experimental results have shown that the boosted causal embeddings outperform several state-of-the-arts significantly on both English and Chinese. As by-products, the top-ranked patterns coincide with human intuition about causality.