Diachrony-aware Induction of Binary Latent Representations from Typological Features
Diachrony-aware Induction of Binary Latent Representations from Typological Features
复制标题
DOI：
--
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
Yugo Murawaki
中科院分区：
文献类型：
--
作者：
Yugo Murawaki
虽然语言类型学的特征是一种很有希望的替代词汇证据来追踪语言的进化历史，但数据集中的大量缺失值给统计建模带来了严重的困难。在本文中，我们结合了两种现有的方法来解决这个问题：(1)关注特征之间相互依赖的共时方法和(2)利用系统发育和/或空间相关语言的历时方法。具体地说，我们提出了一个贝叶斯模型，该模型(1)将每种语言表示为编码特征间依赖关系的二进制潜在参数序列，(2)将语言的参数与其系统发育和空间邻居的参数相关联。实验表明，所提出的模型比其他模型更准确地恢复缺失值，并且归纳表示保留了观测到的地物的系统发育和空间信号。
Although features of linguistic typology are a promising alternative to lexical evidence for tracing evolutionary history of languages, a large number of missing values in the dataset pose serious difficulties for statistical modeling. In this paper, we combine two existing approaches to the problem: (1) the synchronic approach that focuses on interdependencies between features and (2) the diachronic approach that exploits phylogenetically- and/or spatially-related languages. Specifically, we propose a Bayesian model that (1) represents each language as a sequence of binary latent parameters encoding inter-feature dependencies and (2) relates a language’s parameters to those of its phylogenetic and spatial neighbors. Experiments show that the proposed model recovers missing values more accurately than others and that induced representations retain phylogenetic and spatial signals observed for surface features.