论文标题
多代理沟通符合自然语言：功能和结构语言学习之间的协同作用
Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning
论文作者
论文摘要
我们提出了一种结合多代理沟通和传统数据驱动的自然语言学习方法的方法，并最终的目标是教授代理商以自然语言与人类进行交流。我们的出发点是经过对通用而不是特定于任务的语言数据培训的语言模型。然后，我们将该模型放置在多代理自我播放的环境中，该环境生成用于调整或调制模型的任务特定奖励，将其转变为任务条件语言模型。我们介绍了一种基于重读语言模型样本的想法结合两种类型的学习的新方法，并表明该方法在视觉参考通信任务中与其他人在与人交流方面的表现优于其他人。最后，我们提出了不同类型的语言漂移的分类法，可以与一组措施一起进行检测。
We present a method for combining multi-agent communication and traditional data-driven approaches to natural language learning, with an end goal of teaching agents to communicate with humans in natural language. Our starting point is a language model that has been trained on generic, not task-specific language data. We then place this model in a multi-agent self-play environment that generates task-specific rewards used to adapt or modulate the model, turning it into a task-conditional language model. We introduce a new way for combining the two types of learning based on the idea of reranking language model samples, and show that this method outperforms others in communicating with humans in a visual referential communication task. Finally, we present a taxonomy of different types of language drift that can occur alongside a set of measures to detect them.
