模拟词形变化的神经通信实验发现，发音约束促发连接式构词，语言自发融合语法属性。
Discovering Properties of Inflectional Morphology in Neural Emergent Communication
- 在小词汇量下设计新通信游戏，模拟自然语言的双层结构
- 发现发音约束促使语言采用连接式构词方式
- 语言自发融合语法属性，与自然语言趋势一致
基于深度神经网络的涌现通信（EmCom）有望揭示人类语言的本质，但现有研究多聚焦特定子领域目标和指标，偏好一对一映射属性并进行句法组合。为此，我们重新审视常见的属性-值重构游戏，通过施加小词汇量约束以模拟双层结构，并提出一种类自然语言词形变化的新设定，实现与自然语言通信方案的有意义对比。我们设计了新度量标准，探索受真实词形变化特性启发的游戏变体：连接性与融合性。实验发现，模拟语音约束可促进连接式构词，而涌现语言表现出与自然语言相似的语法属性融合倾向。
原文摘要 · Abstract (English)
Emergent communication (EmCom) with deep neural network-based agents promises to yield insights into the nature of human language, but remains focused primarily on a few subfield-specific goals and metrics that prioritize communication schemes which represent attributes with unique characters one-to-one and compose them syntactically. We thus reinterpret a common EmCom setting, the attribute-value reconstruction game, by imposing a small-vocabulary constraint to simulate double articulation, and formulating a novel setting analogous to naturalistic inflectional morphology (enabling meaningful comparison to natural language communication schemes). We develop new metrics and explore variations of this game motivated by real properties of inflectional morphology: concatenativity and fusion. Through our experiments, we discover that simulated phonological constraints encourage concatenative morphology, and emergent languages replicate the tendency of natural languages to fuse grammatical attributes.
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。