首页> 外文会议>Computational intelligence >GETTING CLOSER TO HUMAN LEVEL HUMAN-LIKENESS AND ITS RELATION TO HUMOR IN NON-TASK ORIENTED DIALOGUE SYSTEMS
【24h】

GETTING CLOSER TO HUMAN LEVEL HUMAN-LIKENESS AND ITS RELATION TO HUMOR IN NON-TASK ORIENTED DIALOGUE SYSTEMS

机译:在非任务定向对话系统中更接近人类水平及其与幽默的关系

获取原文
获取原文并翻译 | 示例

摘要

Human-likeness of dialogue systems is an important,rnalbeit neglected issue. In this paper, basing on evaluationrnexperiments of humor-equipped chatterbot, we propose arnmethod of measuring the distance between humans andrnsystems and relation between human-likeness and humor.rnThe results show that the presence of humor can enhancernthe performance of dialogue systems. A humor-equippedrnchatterbot was evaluated as more human like andrngenerally better than one without humor, by both first andrnthird person evaluators. The implications of this fact andrnnovelty of evaluation method are discussed, and somernideas for the future are given.
机译:对话系统的人性化是一个重要的,尽管被忽视的问题。本文在对装备有幽默感的聊天机器人进行评价的基础上,提出了测量人与系统之间的距离以及人类相似性与幽默之间关系的方法。研究结果表明,幽默的存在可以增强对话系统的性能。第一人称和第三人称评估者对配备了幽默感的打扰程序机器人的评价都比没有幽默感的人更喜欢人类,并且通常比没有幽默的人更喜欢。讨论了这一事实的含义和评估方法的新颖性,并提出了对未来的一些想法。

著录项

  • 来源
    《Computational intelligence》|2009年|p.7-14|共8页
  • 会议地点 HonoluluHI(US);HonoluluHI(US)
  • 作者单位

    Graduate School of Media Science and Technology Hokkaido UniversityrnKita 14 Nishi 9, Kita-ku, 060-0814 Sapporo Japan paweldybala@media.eng.hokudai.ac.jp;

    Graduate School of Media Science and Technology Hokkaido University Kita 14 Nishi 9, Kita-ku, 060-0814 SapporornJapan ptaszynski@media.eng.hokudai.ac.jp;

    Graduate School of Media Science and Technology Hokkaido University Kita 14 Nishi 9, Kita-ku, 060-0814 Sapporo Japan kabura@media.eng.hokudai.ac.jp;

    Graduate School of Media Science and Technology Hokkaido University Kita 14 Nishi 9, Kita-ku, 060-0814 Sapporo Japan araki@media.eng.hokudai.ac.jp;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 人工智能理论;
  • 关键词

    artificial intelligence; human-computer interaction; evaluation methods;

    机译:人工智能;人机交互;评估方法;

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