首页> 外文会议>Conference on Computational Natural Language Learning >'LazImpa': Lazy and Impatient neural agents learn to communicate efficiently
【24h】

'LazImpa': Lazy and Impatient neural agents learn to communicate efficiently

机译:'Lazimpa':懒惰和不耐烦的神经电音学会有效地沟通

获取原文

摘要

Previous work has shown that artificial neural agents naturally develop surprisingly non-efficient codes. This is illustrated by the fact that in a referential game involving a speaker and a listener neural networks optimizing accurate transmission over a discrete channel, the emergent messages fail to achieve an optimal length. Furthermore, frequent messages tend to be longer than infrequent ones, a pattern contrary to the Zipf Law of Abbreviation (ZLA) observed in all natural languages. Here, we show that near-optimal and ZLA-compatible messages can emerge, but only if both the speaker and the listener are modified. We hence introduce a new communication system, "Lazlmpa", where the speaker is made increasingly lazy, i.e., avoids long messages, and the listener impatient, i.e., seeks to guess the intended content as soon as possible.
机译:以前的工作表明,人工神经元件自然地发展出令人惊讶的非有效代码。这通过了涉及扬声器的参考游戏和优化在离散信道上的准确传输的引用游戏中,所得消息无法实现最佳长度。此外,频繁的消息往往比不频繁的消息更长,与所有自然语言中观察到的缩写(ZLA)的Zipf法则相反的模式。在这里,我们显示近乎最佳和ZLA兼容的消息可以出现,但只有扬声器和侦听器都被修改。因此,我们介绍了一个新的通信系统,“Lazlmpa”,扬声器越来越懒惰,即避免长消息,听众不耐烦,即,寻求尽快猜测预期的内容。

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