论文标题
寻找异形：斯拉夫历史语音中的连续和离散语言嵌入
In search of isoglosses: continuous and discrete language embeddings in Slavic historical phonology
论文作者
论文摘要
本文研究了神经网络体系结构在多语言环境中有效学习历时语音概括的能力。我们使用三种不同类型的语言嵌入（密集，sigmoid and rotainer-through）采用模型。我们发现，直通模型在准确性方面优于另外两个模型，但是Sigmoid模型的语言嵌入显示了与斯拉夫语言的传统亚组的最强一致性。我们发现，直通模型已经学习了有关声音变化的连贯，半解剖的信息，以及用于未来研究的轮廓方向。
This paper investigates the ability of neural network architectures to effectively learn diachronic phonological generalizations in a multilingual setting. We employ models using three different types of language embedding (dense, sigmoid, and straight-through). We find that the Straight-Through model outperforms the other two in terms of accuracy, but the Sigmoid model's language embeddings show the strongest agreement with the traditional subgrouping of the Slavic languages. We find that the Straight-Through model has learned coherent, semi-interpretable information about sound change, and outline directions for future research.
