Future Event Generation aims to generate fluent and reasonable future event descriptions given preceding events. It requires not only fluent text generation but also commonsense reasoning to maintain the coherence of the entire event story. However, existing FEG methods are easily trapped into repeated or general events without imposing any logical constraint to the generation process. In this paper, we propose a novel explainable FEG framework that consists of a commonsense inference model (IM) and an event generation model (GM). The IM, which is pre-trained on a commonsense knowledge graph ATOMIC, learns to interpret the preceding events and conducts commonsense reasoning to reveal the characters psychology such as intent, reaction, and needs as latent variables. GM further takes the commonsense knowledge as prompts to guide and enforce the generation of logistically coherent future events. As unique merit, the commonsense prompts can be further decoded into textual descriptions, yielding explanations for the future event. Automatic and human evaluation demonstrate that our approach can generate more coherent, specific, and logical future events than the strong baselines.
翻译:未来事件生成的目的是根据前几次事件生成流畅和合理的未来事件描述,不仅需要流畅的文本生成,还需要常识推理来保持整个事件故事的一致性,然而,现有的FEG方法很容易被困在重复或一般事件之中,而不会给生成过程造成任何逻辑上的制约。在本文中,我们提出一个新的、可解释的FEG框架,由常识推理模型和事件生成模型(GM)组成。IM在通用知识图ATOMIC上预先培训,学会解释前几次事件,并进行常识推理,以揭示特征心理学,如意图、反应和需求,作为潜在变量。全球机制还把常识知识作为引导和执行后勤上协调一致的未来事件的导力。作为独特的优点,常识提示可以进一步解译成文字描述,为未来事件提供解释。自动和人类评价表明,我们的方法可以产生比强力基线更连贯、更具体和更符合逻辑的未来事件。