arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1202.3728cs.AI
收藏

关于RoboCup足球叙事的推理

Reasoning about RoboCup Soccer Narratives

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);IBM Watson Research Center(IBM沃森研究中心)

Hannaneh Hajishirzi, Julia Hockenmaier, Erik T. Mueller, Eyal Amir

摘要:

本文提出了一种学习翻译简单叙述的方法,即,将描述动态系统的文本(句子序列)转换为连贯的事件序列,而不需要标记的训练数据。我们的方法采用领域知识的形式的先决条件和事件的影响,我们表明,它优于国家的最先进的监督学习系统的任务,重建机器人足球比赛从他们的评论。

英文摘要:

This paper presents an approach for learning to translate simple narratives, i.e., texts (sequences of sentences) describing dynamic systems, into coherent sequences of events without the need for labeled training data. Our approach incorporates domain knowledge in the form of preconditions and effects of events, and we show that it outperforms state-of-the-art supervised learning systems on the task of reconstructing RoboCup soccer games from their commentaries.

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。

↑