Learning Noun Phrase Anaphoricity in Coreference Resolution via Label Propagation
Learning Noun Phrase Anaphoricity in Coreference Resolution via Label Propagation
复制标题
DOI：
10.1007/s11390-011-9413-x
复制
发表时间：
2011
影响因子：
0.7
通讯作者：
Guodong Zhou;Fang Kong
中科院分区：
文献类型：
--
作者：
Guodong Zhou;Fang Kong
名词短语回指的知识在共指解析中可能是有益的，以绕过非回指名词短语的解析。然而，令人惊讶的是，最近将自动获得的回指信息合并到共指解析系统中的尝试与预期相去甚远。为了提高基于学习的指代消解能力，提出了一种通过标签传播算法确定名词短语指代性的全局学习方法。为了消除标签传播算法的巨大计算量，我们使用加权支持向量作为关键实例来表示训练文本中所有带有指代性标签的NP实例。此外，还探索了两种核函数，即基于特征的径向基函数核和近似匹配的卷积树核来计算两个名词短语之间的指代相似度。在ACE2003语料库上的实验表明，该方法在名词短语的指代性确定及其在基于学习的指代消解中的应用是非常有效的。
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 coreference 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 to represent all the anaphoricity-labeled NP instances in the training texts. In addition, two kinds of kernels, i.e., 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.