...
首页> 外文期刊>Journal of Information Security Research >A Multiple Utterances based Neural Network Model for Joint Intent Detection and Slot Filling
【24h】

A Multiple Utterances based Neural Network Model for Joint Intent Detection and Slot Filling

机译:基于多个基于词的神经网络模型,用于联合意图检测和槽填充

获取原文
获取原文并翻译 | 示例
           

摘要

Spoken language understanding(SLU), which usually involves slot filling and intent detection, is an important task in natural language processing. Most of the state-of-the-art methods are usually take single utterance as input, which would introduce much ambiguity because the loss of context information. To address this issue, we propose a new neural network based joint intent detection and slot filling model which takes multiple utterances as input. In our method, we use an utterance2utterance attention mechanism to combine the information of multiple continuous utterances. We also combine the intent information to the slot filling process with a gating mechanism. Using this proposed model, we participated in the task2 of CCKS2018. Finally, our model ranks NO.2 among the hugely competitive models.
机译:语音语言理解(SLU)通常涉及插槽填充和意图检测,是自然语言处理中的重要任务。大多数最先进的方法通常会将单一话语作为输入,这将引入大量模棱两可,因为丢失上下文信息。为了解决这个问题,我们提出了一种新的基于神经网络的联合意图检测和插槽填充模型,其将多个话语呈现为输入。在我们的方法中,我们使用一个话语温度注意机制来结合多个连续话语的信息。我们还将目的信息与选通机构组合到插槽填充过程中。使用这个提出的模型,我们参与了CCKS2018的Task2。最后,我们的模型在竞争力的模型中排名第2号。

著录项

  • 来源
    《Journal of Information Security Research》 |2020年第2期|54-60|共7页
  • 作者单位

    School of Computer Science and Engineering Northeastern University Shenyang 110169 China;

    School of Computer Science and Engineering Northeastern University Shenyang 110169 China;

    School of Computer Science and Engineering Northeastern University Shenyang 110169 China;

    School of Computer Science and Engineering Northeastern University Shenyang 110169 China;

    School of Computer Science and Engineering Northeastern University Shenyang 110169 China;

    School of Computer Science and Engineering Northeastern University Shenyang 110169 China;

    School of Computer Science and Engineering Northeastern University Shenyang 110169 China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Intent Detection; Slot Filling; Neural Network; Attention Mechanism;

    机译:意图检测;插槽填充;神经网络;注意机制;

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