Generating new events given context with correlated ones plays a crucial role
in many event-centric reasoning tasks. Existing works either limit their scope
to specific scenarios or overlook event-level correlations. In this paper, we
propose to pre-train a general Correlation-aware context-to-Event Transformer
(ClarET) for event-centric reasoning. To achieve this, we propose three novel
event-centric objectives, i.e., whole event recovering, contrastive
event-correlation encoding and prompt-based event locating, which highlight
event-level correlations with effective training. The proposed ClarET is
applicable to a wide range of event-centric reasoning scenarios, considering
its versatility of (i) event-correlation types (e.g., causal, temporal,
contrast), (ii) application formulations (i.e., generation and classification),
and (iii) reasoning types (e.g., abductive, counterfactual and ending
reasoning). Empirical fine-tuning results, as well as zero- and few-shot
learning, on 9 benchmarks (5 generation and 4 classification tasks covering 4
reasoning types with diverse event correlations), verify its effectiveness and
generalization ability.

本文提出了一种预训练的名为 ClarET 的通用事件感知上下文到事件转换器，以解决许多事件中心推理任务中上下文关联事件的生成问题。该方法具有很强的一般适用性和有效性。