Analogous Process Structure Induction for Sub-event Sequence Prediction
Analogous Process Structure Induction for Sub-event Sequence Prediction
复制标题
子事件序列预测的类似过程结构归纳
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
D. Roth
中科院分区：
文献类型：
--
作者：
Hongming Zhang;Muhao Chen;Haoyu Wang;Yangqiu Song;D. Roth
事件理解的计算和认知研究表明，识别、理解和预测事件依赖于对事件序列的结构化表示，以及将其组成部分概念化（抽象）为（软）事件类别。因此，关于一个已知过程（如“买车”）的知识可以用在一个新的类似过程（如“买房”）的上下文中。然而，NLP中的大多数事件理解工作仍然处于底层，没有考虑抽象。在本文中，我们提出了一个类似的过程结构归纳APSI框架，该框架利用过程之间的类比和子事件实例的概念化来预测以前未见过的开放域过程的整个子事件序列。正如我们的实验和分析所表明的，APSI支持为不可见的过程生成有意义的子事件序列，并可以帮助预测缺失的事件。
Computational and cognitive studies of event understanding suggest that identifying, comprehending, and predicting events depend on having structured representations of a sequence of events and on conceptualizing (abstracting) its components into (soft) event categories. Thus, knowledge about a known process such as "buying a car" can be used in the context of a new but analogous process such as "buying a house". Nevertheless, most event understanding work in NLP is still at the ground level and does not consider abstraction. In this paper, we propose an Analogous Process Structure Induction APSI framework, which leverages analogies among processes and conceptualization of sub-event instances to predict the whole sub-event sequence of previously unseen open-domain processes. As our experiments and analysis indicate, APSI supports the generation of meaningful sub-event sequences for unseen processes and can help predict missing events.
DOI：
10.18653/v1/p18-1043
发表时间：
2018-05
期刊：
ArXiv
影响因子：
--
作者：
Hannah Rashkin;Maarten Sap;Emily Allaway;Noah A. Smith;Yejin Choi
通讯作者：
Hannah Rashkin;Maarten Sap;Emily Allaway;Noah A. Smith;Yejin Choi