Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency
Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency
复制标题
DOI：
10.3115/1218955.1219016
复制
发表时间：
2004-07
期刊：
影响因子：
--
通讯作者：
D. Klein;Christopher D. Manning
中科院分区：
文献类型：
--
作者：
D. Klein;Christopher D. Manning
我们提出了依赖结构无监督学习的生成模型。我们还描述了该依赖模型与线性选区模型的乘法组合。产品模型在各自的评估指标上优于这两个组件，给出了无监督依赖解析和无监督选区解析的最佳公开数据。我们还证明了组合模型在跨语言上是有效的，并且是健壮的，能够利用数据中显着的附件或分布规律。
We present a generative model for the unsupervised learning of dependency structures. We also describe the multiplicative combination of this dependency model with a model of linear constituency. The product model outperforms both components on their respective evaluation metrics, giving the best published figures for unsupervised dependency parsing and unsupervised constituency parsing. We also demonstrate that the combined model works and is robust cross-linguistically, being able to exploit either attachment or distributional regularities that are salient in the data.