• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Acoustics, Speech and Signal Processing >Dialogue History Integration into End-to-End Signal-to-Concept Spoken Language Understanding Systems
【24h】

Dialogue History Integration into End-to-End Signal-to-Concept Spoken Language Understanding Systems

机译：对话历史集成到端到端的信号到概念口语理解系统

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This work investigates the embeddings for representing dialog history in spoken language understanding (SLU) systems. We focus on the scenario when the semantic information is extracted directly from the speech signal by means of a single end-to-end neural network model. We proposed to integrate dialogue history into an end-to-end signal-to-concept SLU system. The dialog history is represented in the form of dialog history embedding vectors (so-called h-vectors) and is provided as an additional information to end-to-end SLU models in order to improve the system performance. Three following types of h-vectors are proposed and experimentally evaluated in this paper: (1) supervised-all embeddings predicting bag-of-concepts expected in the answer of the user from the last dialog system response; (2) supervised-freq embeddings focusing on predicting only a selected set of semantic concept (corresponding to the most frequent errors in our experiments); and (3) unsupervised embeddings. Experiments on the MEDIA corpus for the semantic slot filling task demonstrate that the proposed h-vectors improve the model performance.
机译：这项工作调查了在口语理解（SLU）系统中表示对话历史的嵌入。我们关注的是通过单个端到端神经网络模型直接从语音信号中提取语义信息的情况。我们建议将对话历史记录集成到端到端的信号到概念SLU系统中。对话历史以对话历史嵌入向量（所谓的h向量）的形式表示，并作为端到端SLU模型的附加信息提供，以提高系统性能。提出了以下三种类型的h向量，并在实验中进行了实验评估：（1）有监督的所有嵌入，预测从上一次对话系统响应中用户的答案中预期的概念包; （2）有监督频率的嵌入仅着眼于预测一组语义概念（对应于我们实验中最常见的错误）; （3）无监督的嵌入。对MEDIA语料库进行语义空缺填充任务的实验表明，提出的h向量可提高模型性能。

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