首页> 外文会议>Workshop on Extra-Propositional Aspects of Meaning in Computational Linguistics 2012 >Bridging the Gap Between Scope-based and Event-based Negation/Speculation Annotations: A Bridge Not Too Far
【24h】

Bridging the Gap Between Scope-based and Event-based Negation/Speculation Annotations: A Bridge Not Too Far

机译:缩小基于作用域和基于事件的否定/推测注释之间的差距:桥梁不远

获取原文
获取原文并翻译 | 示例

摘要

We study two approaches to the marking of extra-propositional aspects of statements in text: the task-independent cue-and-scope representation considered in the CoNLL-2010 Shared Task, and the tagged-event representation applied in several recent event extraction tasks. Building on shared task resources and the analyses from state-of-the-art systems representing the two broad lines of research, we identify specific points of mismatch between the two perspectives and propose ways of addressing them. We demonstrate the feasibility of our approach by constructing a method that uses cue-and-scope analyses together with a small set of features motivated by data analysis to predict event negation and speculation. Evaluation on BioNLP Shared Task 2011 data indicates the method to outperform the negation/speculation components of state-of-the-art event extraction systems.
机译:我们研究了两种标记文本中语句的命题外方式的方法:CoNLL-2010共享任务中考虑的与任务无关的提示和作用域表示,以及在多个近期事件提取任务中应用的标记事件表示。在共享任务资源和代表两个广泛研究领域的最新系统分析的基础上,我们确定了两种观点之间的不匹配之处,并提出了解决这些观点的方法。我们通过构造一种方法来证明我们方法的可行性,该方法使用提示分析和范围分析以及数据分析所激发的一小部分功能来预测事件否定和推测。对BioNLP Shared Task 2011数据的评估表明,该方法的性能优于最新事件提取系统的否定/推测组件。

著录项

  • 来源
  • 会议地点 Jeju Island(KR)
  • 作者单位

    Department of Computer Science, University of Tokyo, Tokyo, Japan;

    School of Computer Science, University of Manchester, Manchester, United Kingdom,National Centre for Text Mining, University of Manchester, Manchester, United Kingdom;

    School of Computer Science, University of Manchester, Manchester, United Kingdom,National Centre for Text Mining, University of Manchester, Manchester, United Kingdom;

    School of Computer Science, University of Manchester, Manchester, United Kingdom,National Centre for Text Mining, University of Manchester, Manchester, United Kingdom;

    School of Computer Science, University of Manchester, Manchester, United Kingdom,National Centre for Text Mining, University of Manchester, Manchester, United Kingdom,Microsoft Research Asia, Beijing, People's Republic of China;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

  • 入库时间 2022-08-26 14:23:30

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号