东篱科研大数据发现系统（DRDS）

位置：成果数据库 > 期刊 > 期刊详情页

Learning Noun Phrase Anaphoricity in Coreference Resolution via Label Propagation

ISSN号：1000-9000
期刊名称：Journal of Computer Science and Technology
时间：2011.1.1
页码：34-44
分类：TP391[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术] TP391.12[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术]
作者机构：[1]NLP Lab, School of Computer Science and Technology, Soochow University, Suzhou 215006, China
相关基金：Regular Paper Supported by the National Natural Science Foundation of China under Grant Nos. 60873150, 90920004 and 61003153.
相关项目：基于句法结构和语义信息的指代消解研究

关键词：名词短语, 指代消解, 学习方法, 标签, 繁殖, 径向基函数, BP算法, 传播算法, coreference resolution, anaphoricity determination, label propagation, RBF kernel, convolution tree kernel

中文摘要：

名词短语 anaphoricity 的知识可能有利地在 coreference 分辨率被利用绕过非首语重复法的名词短语的决定。然而，它令人吃惊注意到自动地合并的最近的尝试获得了 anaphoricity 信息进 coreference 决定系统远离期望。这份报纸在经由一个标签繁殖算法决定名词短语的 anaphoricity 改进学习底 coreference 分辨率建议一个全球学习方法。以便在标签繁殖算法消除巨大的计算负担，我们作为批评例子采用加权的支持向量在训练文章代表所有标记 anaphoricity 的 NP 例子。另外，二种内核，即，基于特征的 RBF (光线的基础函数) 有近似匹配的核和卷绕旋转树内核，被探索计算二个名词短语的 anaphoricity 类似。ACE2003 语料库的实验在学习底 coreference 分辨率在名词短语和它的申请的 anaphoricity 决心表明我们的方法的大有效性。

英文摘要：

Knowledge of noun phrase anaphoricity might be profitably exploited in coreference resolution to bypass the resolution of non-anaphoric noun phrases. However, it is surprising to notice that recent attempts to incorporate automatically acquired anaphoricity information into coreferenee resolution systems have been far from expectation. This paper proposes a global learning method in determining the anaphoricity of noun phrases via a label propagation algorithm to improve learning-based coreference resolution. In order to eliminate the huge computational burden in the label propagation algorithm, we employ the weighted support vectors as the critical instances in the training texts. In addition, two kinds of kernels, i.e instances to represent all the anaphoricity-labeled NP , the feature-based RBF （Radial Basis Function） kernel and the convolution tree kernel with approximate matching, are explored to compute the anaphoricity similarity between two noun phrases. Experiments on the ACE2003 corpus demonstrate the great effectiveness of our method in anaphoricity determination of noun phrases and its application in learning-based coreference resolution.

同期刊论文项目