• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computer speech and language >Semantic vector learning for natural language understanding
【24h】

Semantic vector learning for natural language understanding

机译：语义向量学习，自然语言理解

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

Natural language understanding (NLU) is a core technology for implementing natural interfaces and has received much attention in recent years. While learning embedding models has yielded fruitful results in several NLP subfields, most notably Word2-Vec, embedding correspondence has relatively not been well explored especially in the context of NLU, a task that typically extracts structured semantic knowledge from a text. A NLU embedding model can facilitate analyzing and understanding relationships between unstructured texts and their corresponding structured semantic knowledge, essential for both researchers and practitioners of NLU. Toward this end, we propose a framework that learns to embed semantic correspondence between text and its extracted semantic knowledge, called semantic frame. One key contributed technique is semantic frame reconstruction used to derive a one-to-one mapping between embedded vectors and their corresponding semantic frames. Embedding into semantically meaningful vectors and computing their distances in vector space provides a simple, but effective way to measure semantic similarities. With the proposed framework, we demonstrate three key areas where the embedding model can be effective: visualization, distance based semantic search, similarity-based intent classification and re-ranking. (C) 2019 Elsevier Ltd. All rights reserved.
机译：自然语言理解（NLU）是用于实现自然界面的核心技术，近年来受到了很多关注。虽然学习嵌入模型已在多个NLP子字段（最著名的是Word2-Vec）中取得了丰硕的成果，但相对而言，尤其在NLU（通常从文本中提取结构化语义知识的任务）的情况下，嵌入对应关系还没有得到很好的研究。 NLU嵌入模型可以促进分析和理解非结构化文本及其对应的结构化语义知识之间的关系，这对于NLU的研究人员和从业人员都是必不可少的。为此，我们提出了一个框架，该框架学习在文本与其提取的语义知识之间嵌入语义对应关系，称为语义框架。一种关键的贡献技术是语义框架重构，该语义框架重构用于得出嵌入向量及其对应的语义框架之间的一对一映射。嵌入语义上有意义的向量中并计算它们在向量空间中的距离，提供了一种简单但有效的方法来测量语义相似性。通过提出的框架，我们演示了嵌入模型可以有效发挥的三个关键领域：可视化，基于距离的语义搜索，基于相似度的意图分类和重新排序。 （C）2019 Elsevier Ltd.保留所有权利。

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