arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.02247cs.CLcs.AI
收藏

STaCK:基于时间常识知识的句子排序

STaCK: Sentence Ordering with Temporal Commonsense Knowledge

University of Michigan(密歇根大学);Singapore University of Technology and Design(新加坡科技设计大学)

Deepanway Ghosal, Navonil Majumder, Rada Mihalcea, Soujanya Poria

摘要:

句子顺序预测是在随机排序的文档中找到句子的正确顺序的任务。正确排列句子需要理解与文本中描述的事件的时间顺序相关的连贯性。围绕这些事件的文档级上下文理解和常识知识通常是揭示这种连贯性和预测确切时间顺序的关键。在本文中,我们介绍STaCK -一个框架的基础上图神经网络和时间常识知识的模型全局信息和预测相对顺序的句子。我们的图形网络使用“过去”和“未来”的知识积累时间证据,并将句子排序作为一个约束边缘分类问题。我们报告了五个不同数据集的结果,并根据经验表明,所提出的方法自然适合于订单预测。这项工作的实施情况可在https://github.com/declare-lab/sentence-ordering上公开查阅。

英文摘要:

Sentence order prediction is the task of finding the correct order of sentences in a randomly ordered document. Correctly ordering the sentences requires an understanding of coherence with respect to the chronological sequence of events described in the text. Document-level contextual understanding and commonsense knowledge centered around these events are often essential in uncovering this coherence and predicting the exact chronological order. In this paper, we introduce STaCK -- a framework based on graph neural networks and temporal commonsense knowledge to model global information and predict the relative order of sentences. Our graph network accumulates temporal evidence using knowledge of `past' and `future' and formulates sentence ordering as a constrained edge classification problem. We report results on five different datasets, and empirically show that the proposed method is naturally suitable for order prediction. The implementation of this work is publicly available at: https://github.com/declare-lab/sentence-ordering.

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。

↑