Weakly Supervised Subevent Knowledge Acquisition
Weakly Supervised Subevent Knowledge Acquisition
复制标题
DOI：
10.18653/v1/2020.emnlp-main.430
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Wenlin Yao;Zeyu Dai;Maitreyi Ramaswamy;Bonan Min;Ruihong Huang
中科院分区：
文献类型：
--
作者：
Wenlin Yao;Zeyu Dai;Maitreyi Ramaswamy;Bonan Min;Ruihong Huang
子事件详细描述事件，并广泛存在于事件描述中。子事件知识对于语篇分析和以事件为中心的应用是有用的。考虑到子事件知识的稀缺性，我们提出了一种弱监督的方法来从文本中提取子事件关系元组，并建立了第一个大规模的子事件知识库。我们首先通过利用1)子事件在时间上包含在父事件中，以及2)父事件的定义可用于进一步指导子事件的识别的两个观测，来获得可能具有子事件关系的事件对的初始集合。然后，我们利用初始的种子子事件对收集丰富的弱监督，使用BERT训练上下文分类器，并应用该分类器识别新的子事件对。评估表明，获得的次事件元组(239K)质量高(准确率为90.1%)，涵盖了广泛的事件类型。所获得的次事件知识已被证明对语篇分析和识别一系列事件-事件关系很有用。
Subevents elaborate an event and widely exist in event descriptions. Subevent knowledge is useful for discourse analysis and event-centric applications. Acknowledging the scarcity of subevent knowledge, we propose a weakly supervised approach to extract subevent relation tuples from text and build the first large scale subevent knowledge base. We first obtain the initial set of event pairs that are likely to have the subevent relation, by exploiting two observations that 1) subevents are temporally contained by the parent event, and 2) the definitions of the parent event can be used to further guide the identification of subevents. Then, we collect rich weak supervision using the initial seed subevent pairs to train a contextual classifier using BERT and apply the classifier to identify new subevent pairs. The evaluation showed that the acquired subevent tuples (239K) are of high quality (90.1% accuracy) and cover a wide range of event types. The acquired subevent knowledge has been shown useful for discourse analysis and identifying a range of event-event relations.