A Fully-Lexicalized Probabilistic Model for Japanese Zero Anaphora Resolution
A Fully-Lexicalized Probabilistic Model for Japanese Zero Anaphora Resolution
复制标题
DOI：
10.3115/1599081.1599178
复制
发表时间：
2008-08
期刊：
影响因子：
--
通讯作者：
Ryohei Sasano;Daisuke Kawahara;S. Kurohashi
中科院分区：
文献类型：
--
作者：
Ryohei Sasano;Daisuke Kawahara;S. Kurohashi
本文提出了一个日语零形回指消解的概率模型。首先，该模型识别话语实体并将所有提及与它们联系起来。零代词检测的基础上自动构建的情况框架的情况结构分析。他们的适当的先行词是从具有高显着性分数的实体中选择的，基于格框架和对零代词和先行词之间的关系的几个偏好。基于概率评价指标同时确定格结构和零回指关系。
This paper presents a probabilistic model for Japanese zero anaphora resolution. First, this model recognizes discourse entities and links all mentions to them. Zero pronouns are then detected by case structure analysis based on automatically constructed case frames. Their appropriate antecedents are selected from the entities with high salience scores, based on the case frames and several preferences on the relation between a zero pronoun and an antecedent. Case structure and zero anaphora relation are simultaneously determined based on probabilistic evaluation metrics.