时序事件序列的条件生成
Conditional Generation of Temporally-ordered Event Sequences
摘要:
叙事图式知识的模型已被证明是有用的一系列事件相关的任务,但他们通常不捕捉事件之间的时间关系。我们提出了一个单一的模型,解决时间排序,排序给定的事件到他们发生的顺序,和事件填充,预测新的事件,适合现有的时间顺序序列。我们使用了一个基于BART的条件生成模型,它可以捕获时间性和共同事件共现,这意味着它可以灵活地应用于这个空间中的不同任务。我们的模型被训练成一个去噪自动编码器:我们获取时间顺序的事件序列,将它们打乱,删除一些事件,然后尝试恢复原始事件序列。此任务教导模型在给定关于基础场景中事件的不完整知识的情况下进行推断。在时间排序任务中,我们证明了我们的模型能够在不访问显式标记的时间训练数据的情况下从现有数据集中解读事件序列,优于基于BERT的成对模型和基于BERT的指针网络。在事件填充上,人类评估表明,与GPT-2故事完成模型相比,我们的模型能够生成在时间上更适合输入事件的事件。
英文摘要:
Models of narrative schema knowledge have proven useful for a range of event-related tasks, but they typically do not capture the temporal relationships between events. We propose a single model that addresses both temporal ordering, sorting given events into the order they occurred, and event infilling, predicting new events which fit into an existing temporally-ordered sequence. We use a BART-based conditional generation model that can capture both temporality and common event co-occurrence, meaning it can be flexibly applied to different tasks in this space. Our model is trained as a denoising autoencoder: we take temporally-ordered event sequences, shuffle them, delete some events, and then attempt to recover the original event sequence. This task teaches the model to make inferences given incomplete knowledge about the events in an underlying scenario. On the temporal ordering task, we show that our model is able to unscramble event sequences from existing datasets without access to explicitly labeled temporal training data, outperforming both a BERT-based pairwise model and a BERT-based pointer network. On event infilling, human evaluation shows that our model is able to generate events that fit better temporally into the input events when compared to GPT-2 story completion models.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。