首页> 外文期刊>Computer speech and language >HSCJN: A holistic semantic constraint joint network for diverse response generation
【24h】

HSCJN: A holistic semantic constraint joint network for diverse response generation

机译:HSCJN:用于各种反应生成的整体语义约束联合网络

获取原文
获取原文并翻译 | 示例
       

摘要

The sequence-to-sequence (Seq2Seq) model generates target words iteratively given the previously observed words during the decoding process, which results in the loss of the holistic semantics in the target response and the complete semantic relationship between responses and dialogue histories. In this paper, we propose a generic diversity-promoting joint network, called Holistic Semantic Constraint Joint Network (HSCJN), enhancing the global sentence information, and then regularizing the objective function with penalizing the low entropy output during the training stage. Our network introduces more target information to improve diversity and captures direct semantic information to better constrain relevance simultaneously. Moreover, the proposed method can be easily applied to any Seq2Seq structure. Extensive experiments on several dialogue corpuses show that our method effectively improves both semantic consistency and diversity of generated responses, and achieves better performance than other competitive methods.
机译:序列到序列(SEQ2Seq)模型在解码过程中迭代地产生目标词,这导致目标响应中的整体语义的丢失以及响应和对话历史之间的完整语义关系。在本文中,我们提出了一种通用的多样性促进联合网络​​,称为整体语义约束联合网络(HSCJN),增强了全局句子信息,然后在训练阶段期间惩罚低熵输出来规则地规范目标函数。我们的网络引入了更多目标信息来提高分集,并捕获直接语义信息,同时更好地限制相关性。此外,所提出的方法可以容易地应用于任何SEQ2SEQ结构。关于几种对话语料的广泛实验表明,我们的方法有效提高了产生的响应的语义一致性和多样性,并实现了比其他竞争方法更好的性能。

著录项

  • 来源
    《Computer speech and language》 |2021年第1期|101135.1-101135.10|共10页
  • 作者单位

    Tsinghua Shenzhen International Graduate School Tsinghua University PR China;

    Tsinghua Shenzhen International Graduate School Tsinghua University PR China;

    Tsinghua Shenzhen International Graduate School Tsinghua University PR China Baidu Inc. Beijing PR China;

    Department of Computer Science University of Virginia USA;

    Tsinghua Shenzhen International Graduate School Tsinghua University PR China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Dialogue generation; Diversity; Holistic semantics; Word prediction; Entropy regularizer;

    机译:对话一代;多样性;整体语义;字预测;熵规范器;

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