公开(公告)号：US20130013290A1

公开(公告)日：2013-01-10

申请号：US13531682

申请日：2012-06-25

申请人： Kotaro FUNAKOSHI ,  Mikio NAKANO ,  Takenobu TOKUNAGA ,  Ryu IIDA

发明人： Kotaro FUNAKOSHI ,  Mikio NAKANO ,  Takenobu TOKUNAGA ,  Ryu IIDA

IPC分类号： G06F17/27

CPC分类号： G06F17/279 ,  G10L13/027 ,  G10L15/1822

摘要： A referring expression processor which uses a probabilistic model and in which referring expressions including descriptive, anaphoric and deictic expressions are understood and generated in the course of dialogue is provided. The referring expression processor according to the present invention includes: a referring expression processing section which performs at least one of understanding and generation of referring expressions using a probabilistic model constructed with a referring expression Bayesian network, each referring expression Bayesian network representing relationships between a reference domain (D) which is a set of possible referents, a referent (X) in the reference domain, a concept (C) concerning the referent and a word (W) which represents the concept; and a memory which stores data necessary for constructing the referring expression Bayesian network.

摘要翻译： 提供了一种使用概率模型的引用表达式处理器，其中包括描述性，隐喻性和指示性表达的引用表达在对话过程中被理解和产生。 根据本发明的引用表达式处理器包括：引用表达式处理部分，其使用由参考表达式贝叶斯网络构建的概率模型来执行理解和生成引用表达中的至少一个，每个引用表达式贝叶斯网络表示参考 （D），参考域中的指示（X），涉及对象的概念（C）和表示概念的词（W）; 以及存储器，其存储构造参考表达式贝叶斯网络所需的数据。