• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Conference on empirical methods in natural language processing >Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog
【24h】

Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog

机译：自然语言不会在“多代理”对话框中“自然地”出现

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

摘要

A number of recent works have proposed techniques for end-to-end learning of communication protocols among cooperative multi-agent populations, and have simultaneously found the emergence of grounded human-interpretable language in the protocols developed by the agents, learned without any human supervision! In this paper, using a Task & Talk reference game between two agents as a testbed, we present a sequence of 'negative' results culminating in a 'positive' one - showing that while most agent-invented languages are effective (i.e. achieve near-perfect task rewards), they are decidedly not inter-pretable or compositional. In essence, we find that natural language does not emerge 'naturally', despite the semblance of ease of natural-language-emergence that one may gather from recent literature. We discuss how it is possible to coax the invented languages to become more and more human-like and compositional by increasing restrictions on how two agents may communicate.
机译：最近的许多工作提出了用于在协作多代理群体之间进行端到端通信协议学习的技术，并且同时发现了由代理开发的协议中扎根的人类可解释语言的出现，这些语言是在无需任何人工监督的情况下学习的！在本文中，使用两个特工之间的任务与谈话参考游戏作为测试平台，我们展示了一系列“负”结果，最终形成了一个“正”结果，这表明尽管大多数特工发明的语言都是有效的（即实现近乎完美的任务奖励），它们绝对不是可以相互替代或组成的。从本质上讲，我们发现自然语言并不是“自然地”出现的，尽管人们可能从最近的文献中收集到自然语言出现的易用性。我们讨论了如何通过增加对两个代理进行通信的限制来诱使所发明的语言变得越来越像人类，并且变得更加人性化。

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