搜索结果: 1-6 共查到“语法学 Grammar Induction”相关记录6条 . 查询时间(0.046 秒)
Natural Language Grammar Induction using a Constituent-Context Model
Natural Language Grammar Induction Constituent
2015/6/12
This paper presents a novel approach to the unsupervised learning of syntactic analyses of natural language text. Most previous work has focused on maximizing likelihood according to generative PCFG m...
A Generative Constituent-Context Model for Improved Grammar Induction
Generative Constituent Context Model Grammar Induction
2015/6/12
We present a generative distributional model for the unsupervised induction of natural language syntax which explicitly models constituent yields and contexts. Parameter search with EM produces higher...
Lateen EM: Unsupervised Training with Multiple Objectives,Applied to Dependency Grammar Induction
Lateen EM Unsupervised Training Multiple Objectives Dependency Grammar Induction
2015/6/10
We present new training methods that aim to mitigate local optima and slow convergence in unsupervised training by using additional imperfect objectives. In its simplest form, lateen EM alternates bet...
Capitalization Cues Improve Dependency Grammar Induction
Capitalization Cues Grammar Induction
2015/6/10
We show that orthographic cues can be helpful for unsupervised parsing. In the Penn Treebank, transitions between upper- and lowercase tokens tend to align with the boundaries of base (English) noun p...
Three Dependency-and-Boundary Models for Grammar Induction
Three Dependency Boundary Models Grammar Induction
2015/6/10
We present a new family of models for unsupervised parsing, Dependency and Boundary models, that use cues at constituent boundaries to inform head-outward dependency tree generation. We build on three...
Breaking Out of Local Optima with Count Transforms and Model Recombination: A Study in Grammar Induction
Local Optima Count Transforms Model Recombination Grammar Induction
2015/6/10
Many statistical learning problems in NLP call for local model search methods. But accuracy tends to suffer with current techniques,which often explore either too narrowly or too broadly: hill-climber...