• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>3rd workshop on representation learning for NLP 2018 >A Dense Vector Representation for Open-Domain Relation Tuples
【24h】

A Dense Vector Representation for Open-Domain Relation Tuples

机译：开域关系元组的密集矢量表示

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Open Information Extraction (Open IE), which has been extensively studied as a new paradigm on unrestricted information extraction, produces relation tuples (results) which serve as intermediate structures in several natural language processing tasks, such as question answering system. In this paper, we investigate ways to learn the vector representation of Open IE relation tuples using various approaches, ranging from simple vector composition to more advanced methods, such as recursive autoencoder (RAE). The quality of vector representation was evaluated by conducting experiments on the relation tuple similarity task. While the experiment result shows that simple linear combination (i.e., averaging the vectors of the words participating in the tuple) outperforms any other methods, including RAE, RAE itself has its own advantage in dealing with a case, in which the similarity criterion is characterized by each element in the tuple, where the simple linear combination unable to identify.
机译：开放信息提取（Open IE）作为不受限制的信息提取的一种新范式已得到广泛研究，它产生关系元组（结果），该关系元组在几种自然语言处理任务（例如问题回答系统）中充当中间结构。在本文中，我们研究了使用各种方法来学习Open IE关系元组的矢量表示的方法，从简单的矢量合成到更高级的方法，例如递归自动编码器（RAE）。通过对关系元组相似性任务进行实验来评估向量表示的质量。尽管实验结果表明，简单的线性组合（即，对参与元组的单词的向量进行平均）要优于包括RAE在内的任何其他方法，但RAE本身在处理类似情况（具有相似性标准）时具有自己的优势。由元组中的每个元素组成，其中简单的线性组合无法识别。

著录项

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