Semi-Supervised Noun Compound Analysis with Edge and Span Features
Semi-Supervised Noun Compound Analysis with Edge and Span Features
复制标题
具有边缘和跨度特征的半监督名词复合分析
DOI：
10.1016/j.neures.2009.09.090
复制
发表时间：
2012
影响因子：
2.9
通讯作者：
S. Kurohashi
中科院分区：
文献类型：
--
作者：
Yugo Murawaki;S. Kurohashi
在本文中，我们建议使用的跨度，除了边缘的名词复合分析。跨度是可以表示名词复合词的单词序列。与边相比，跨度在半监督句法分析方面具有良好的性质。它们可以从大量未注释的文本中可靠地提取出来。此外，虽然边缘的组合（如兄弟和祖父母交互）通常难以在解析中处理，但使用任意宽度的跨度非常容易。我们表明，跨度可以直接纳入标准的基于图表的解析算法。我们创建了一个结合边缘和跨度特征的半监督判别式解析器。实验表明，跨度特征提高了准确性，当它们与边缘特征相结合时，获得了进一步的增益。
In this paper, we propose the use of spans in addition to edges in noun compound analysis. A span is a sequence of words that can represent a noun compound. Compared with edges, spans have good properties in terms of semi-supervised parsing. They can be reliably extracted from a huge amount of unannotated text. In addition, while the combinations of edges such as sibling and grandparent interactions are, in general, difficult to handle in parsing, it is quite easy to utilize spans with arbitrary width. We show that spans can be incorporated straightforwardly into the standard chart-based parsing algorithm. We create a semi-supervised discriminative parser that combines edge and span features. Experiments show that span features improve accuracy and that further gain is obtained when they are combined with edge features.