Capturing Salience with a Trainable Cache Model for Zero-anaphora Resolution
Capturing Salience with a Trainable Cache Model for Zero-anaphora Resolution
复制标题
使用可训练的缓存模型捕获显着性以实现零照应分辨率
DOI：
10.3115/1690219.1690237
复制
发表时间：
2009
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
本文探讨了如何将Walker（1996）引入的缓存概念应用于零回指解析任务。我们提出了一种基于机器学习的缓存模型实现，以减少识别先行项的计算成本。我们对日本报纸文章的实证评估表明，每个零代词的候选先行词的数量可以大大减少，同时保持解决它的准确性。
This paper explores how to apply the notion of caching introduced by Walker (1996) to the task of zero-anaphora resolution. We propose a machine learning-based implementation of a cache model to reduce the computational cost of identifying an antecedent. Our empirical evaluation with Japanese newspaper articles shows that the number of candidate antecedents for each zero-pronoun can be dramatically reduced while preserving the accuracy of resolving it.