Anaphora resolution by antecedent identification followed by anaphoricity determination
Anaphora resolution by antecedent identification followed by anaphoricity determination
复制标题
通过先行词识别和照应性确定进行照应解析
DOI：
--
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
Yuji Matsumoto
中科院分区：
文献类型：
--
作者：
R. Iida;Kentaro Inui;Yuji Matsumoto
我们提出了一种基于机器学习的名词短语照应解析方法，该方法结合了先前基于学习的模型的优点，同时克服了它们的缺点。我们的照应解析过程颠倒了 Ng 和 Cardie [2002b] 提出的分类然后搜索模型中的步骤顺序，继承了该模型的所有优点。我们进行了解决日语名词短语照应的实验。结果表明，通过基于选择和分类的修改，我们提出的模型优于早期基于学习的方法。
We propose a machine learning-based approach to noun-phrase anaphora resolution that combines the advantages of previous learning-based models while overcoming their drawbacks. Our anaphora resolution process reverses the order of the steps in the classification-then-search model proposed by Ng and Cardie [2002b], inheriting all the advantages of that model. We conducted experiments on resolving noun-phrase anaphora in Japanese. The results show that with the selection-then-classification-based modifications, our proposed model outperforms earlier learning-based approaches.