arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.06344cs.AI
收藏

未来不是一维的:基于图模型的复杂事件模式归纳

The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction

UIUC(伊利诺伊大学厄巴纳-香槟分校);Virginia Tech(弗吉尼亚理工大学);NYU(纽约大学);US ARL(美国陆军研究实验室)

Manling Li, Sha Li, Zhenhailong Wang, Lifu Huang, Kyunghyun Cho, Heng Ji, Jiawei Han, Clare Voss

摘要:

事件图式对事件及其联系的常规结构的知识进行编码。随着事件的展开,图式作为脚手架至关重要。以前的工作集中在原子事件或线性时间事件序列的事件模式归纳,忽略了事件之间的相互作用,通过参数和参数关系。我们引入了一个新的概念,时间复杂事件模式:一个基于图形的模式表示,包括事件,参数,时间连接和参数关系。此外,我们提出了一个时间事件图模型,预测事件实例的时间复杂事件模式。为了构建和评估这样的模式,我们发布了一个新的模式学习语料库,其中包含6,399个文档,并附有事件图,我们手动构建了黄金标准模式。基于模式匹配和实例图困惑的内在评价,证明了我们的概率图模式库相比线性表示的优越质量。对模式引导的未来事件预测的外部评估进一步证明了我们的事件图模型的预测能力,在HITS@1上显著优于人类模式和基线超过23.8%。

英文摘要:

Event schemas encode knowledge of stereotypical structures of events and their connections. As events unfold, schemas are crucial to act as a scaffolding. Previous work on event schema induction focuses either on atomic events or linear temporal event sequences, ignoring the interplay between events via arguments and argument relations. We introduce a new concept of Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations. In addition, we propose a Temporal Event Graph Model that predicts event instances following the temporal complex event schema. To build and evaluate such schemas, we release a new schema learning corpus containing 6,399 documents accompanied with event graphs, and we have manually constructed gold-standard schemas. Intrinsic evaluations based on schema matching and instance graph perplexity, prove the superior quality of our probabilistic graph schema library compared to linear representations. Extrinsic evaluation on schema-guided future event prediction further demonstrates the predictive power of our event graph model, significantly outperforming human schemas and baselines by more than 23.8% on HITS@1.

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。

↑