Development of a Machine Learnable Discourse Tagging Tool
Development of a Machine Learnable Discourse Tagging Tool
复制标题
机器学习的话语标记工具的开发
DOI：
10.3115/1118078.1118081
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
Y. Niimi
中科院分区：
文献类型：
--
作者：
Masahiro Araki;Yukihiko Kimura;T. Nishimoto;Y. Niimi
我们使用机器学习方法开发了一种用于口语对话语料库的话语级别标记工具。作为话语层面的信息，我们关注对话行为、相关性和话语片段。在对话行为标记中，我们实施了基于转换的学习程序，并在开放测试中获得了 70% 的准确率。在相关性和话语片段标记方面，我们实施了基于决策树的学习程序，准确率分别约为 75% 和 72%。
We have developed a discourse level tagging tool for spoken dialogue corpus using machine learning methods. As discourse level information, we focused on dialogue act, relevance and discourse segment. In dialogue act tagging, we have implemented a transformation-based learning procedure and resulted in 70% accuracy in open test. In relevance and discourse segment tagging, we have implemented a decision-tree based learning procedure and resulted in about 75% and 72% accuracy respectively.