论文标题
在新兴语言中捍卫构图
Defending Compositionality in Emergent Languages
论文作者
论文摘要
传统上，组成性被理解为语言生产力的主要因素，更广泛地是人类认知。然而，最近，一些研究开始质疑其状态，表明即使没有明显的组成行为，人工神经网络也擅长概括。我们认为其中一些结论太强和/或不完整。在两个代理通信游戏的背景下，我们表明，当在适当的数据集上进行评估时，组成性确实对于成功的概括至关重要。
Compositionality has traditionally been understood as a major factor in productivity of language and, more broadly, human cognition. Yet, recently, some research started to question its status, showing that artificial neural networks are good at generalization even without noticeable compositional behavior. We argue that some of these conclusions are too strong and/or incomplete. In the context of a two-agent communication game, we show that compositionality indeed seems essential for successful generalization when the evaluation is done on a proper dataset.
