用无监督翻译破解智能体自动生成的语言，发现任务越复杂越易翻译。
Unsupervised Translation of Emergent Communication
- 用无监督机器翻译技术解析智能体在指代游戏中的自生语言。
- 语义多样性越高，自生语言越容易被翻译，复杂任务中仍可译出实用语义。
- 首次不依赖平行数据实现智能体语言翻译，适合对多智能体系统感兴趣的读者。
自生语言（Emergent Communication, EC）为智能体在共同目标驱动下自主形成语言系统提供了独特窗口。然而，其可解释性差，且与自然语言的关系难以评估。本研究采用无监督神经机器翻译（UNMT）技术，对不同任务复杂度下指代游戏中生成的自生语言进行解码，分析环境语义多样性的影响。结果表明，以语义多样性表征的任务复杂性提升了自生语言的可翻译性；而语义变化受限的高复杂度任务中生成的自生语言具有实用语用特征，虽难解释，但仍具备可翻译性。这是迄今首次在无需平行数据支持下实现自生语言翻译的研究。
原文摘要 · Abstract (English)
Emergent Communication (EC) provides a unique window into the language systems that emerge autonomously when agents are trained to jointly achieve shared goals. However, it is difficult to interpret EC and evaluate its relationship with natural languages (NL). This study employs unsupervised neural machine translation (UNMT) techniques to decipher ECs formed during referential games with varying task complexities, influenced by the semantic diversity of the environment. Our findings demonstrate UNMT's potential to translate EC, illustrating that task complexity characterized by semantic diversity enhances EC translatability, while higher task complexity with constrained semantic variability exhibits pragmatic EC, which, although challenging to interpret, remains suitable for translation. This research marks the first attempt, to our knowledge, to translate EC without the aid of parallel data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。