Accurate Maximum-Margin Training for Parsing With Context-Free Grammars

Accurate Maximum-Margin Training for Parsing With Context-Free Grammars
复制标题

用于上下文无关语法解析的准确最大间隔训练

DOI:
10.1109/tnnls.2015.2497149
复制
发表时间:
2017
影响因子:
10.4
通讯作者:
K.-R. Müller
K.-R. Müller
中科院分区:
计算机科学1区
文献类型:
--
作者:
A. Bauer;M. Braun;K.-R. Müller

文献摘要

参考文献

被引文献

相似文献

自然语言解析的任务可以自然地嵌入到最大余量框架中,使用适当的联合特征映射和适当的结构化损失函数进行结构化输出预测。虽然存在基于切割平面方法的有效学习算法,用于优化具有潜在指数数量的线性约束的所得二次目标,但它们的效率关键取决于用于推断当前迭代中最违反的约束的推理算法。在本文中,我们推导出一个扩展的著名的科克-Kasami-杨格(CKY)算法用于分析与概率上下文无关的语法的情况下,损失增强推理,使有效的培训切割平面的方法。由此产生的算法保证在多项式时间内找到一个最优解,超过CKY算法的运行时间一个术语,这只取决于可能的损失值的数量。为了证明该算法的可行性,我们进行了一组实验,用于分析英语句子。
The task of natural language parsing can naturally be embedded in the maximum-margin framework for structured output prediction using an appropriate joint feature map and a suitable structured loss function. While there are efficient learning algorithms based on the cutting-plane method for optimizing the resulting quadratic objective with potentially exponential number of linear constraints, their efficiency crucially depends on the inference algorithms used to infer the most violated constraint in a current iteration. In this paper, we derive an extension of the well-known Cocke-Kasami-Younger (CKY) algorithm used for parsing with probabilistic context-free grammars for the case of loss-augmented inference enabling an effective training in the cutting-plane approach. The resulting algorithm is guaranteed to find an optimal solution in polynomial time exceeding the running time of the CKY algorithm by a term, which only depends on the number of possible loss values. In order to demonstrate the feasibility of the presented algorithm, we perform a set of experiments for parsing English sentences.
用于形态解析中消歧的概率上下文无关语法
DOI: --
发表时间: 1993
期刊: Conference of the European Chapter of the Association for Computational Linguistics
影响因子: --
作者:
Josée S. Heemskerk
通讯作者: Josée S. Heemskerk
组合范畴语法:生成能力以及与线性上下文无关重写系统的关系
DOI: --
发表时间: 1988
期刊: Annual Meeting of the Association for Computational Linguistics
影响因子: --
作者:
David J. Weir;A. Joshi
通讯作者: A. Joshi
DOI: 10.1109/msp.2013.2249294
发表时间: 2013-06
影响因子: 14.9
作者:
G. Montavon;M. Braun;Tammo Krueger;K. Müller
通讯作者: G. Montavon;M. Braun;Tammo Krueger;K. Müller
概率上下文无关文法的迭代 CKY 解析
DOI: 10.1007/978-3-540-30211-7_6
发表时间: 2004
期刊: Inf. Sci.
影响因子: --
作者:
Yoshimasa Tsuruoka;Junichi Tsujii
通讯作者: Junichi Tsujii
具有高阶损失函数的结构化输出学习
DOI: --
发表时间: 2012
期刊: International Conference on Artificial Intelligence and Statistics
影响因子: --
作者:
Daniel Tarlow;R. Zemel
通讯作者: R. Zemel