arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1605.07133cs.CLcs.CVcs.LG
收藏

基于多智能体通信的语言学习

Towards Multi-Agent Communication-Based Language Learning

University of Trento(特伦托大学)

Angeliki Lazaridou, Nghia The Pham, Marco Baroni

摘要:

我们提出了一个交互式多模态语言学习框架。我们的学习者(实现为前馈神经网络)不是被动地接触大量的自然文本,而是从白板设置开始参与合作参考游戏,从而从交流的需要中发展自己的语言,以便在游戏中取得成功。初步实验提供了有希望的结果,但也表明,重要的是要确保以这种方式训练的代理不会开发出仅对他们正在玩的游戏有效的adhoc通信代码

英文摘要:

We propose an interactive multimodal framework for language learning. Instead of being passively exposed to large amounts of natural text, our learners (implemented as feed-forward neural networks) engage in cooperative referential games starting from a tabula rasa setup, and thus develop their own language from the need to communicate in order to succeed at the game. Preliminary experiments provide promising results, but also suggest that it is important to ensure that agents trained in this way do not develop an adhoc communication code only effective for the game they are playing

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑