Semantic Annotation of Japanese Functional Expressions and its Impact on Factuality Analysis
Semantic Annotation of Japanese Functional Expressions and its Impact on Factuality Analysis
复制标题
DOI：
10.3115/v1/w15-1606
复制
发表时间：
2015-06
期刊：
影响因子：
--
通讯作者：
Yudai Kamioka;Kazuya Narita;Junta Mizuno;M. Kanno;Kentaro Inui
中科院分区：
文献类型：
--
作者：
Yudai Kamioka;Kazuya Narita;Junta Mizuno;M. Kanno;Kentaro Inui
识别函数表达式的含义对于自然语言理解至关重要。由于缺乏足够的机器学习和评估语料库，这是一项艰巨的任务。在本研究中，我们设计了一种新的注释方案，并构建了一个包含 2,327 个日语句子和 8,775 个功能表达的语料库。我们的方案获得了较高的注释者间一致性，kappa 得分为 0.85。在实验中，我们证实基于机器学习的功能表达分析有助于事实分析。
Recognizing the meaning of functional expressions is essential for natural language understanding. This is a difficult task, owing to the lack of a sufficient corpus for machine learning and evaluation. In this study, we design a new annotation scheme and construct a corpus containing 2,327 Japanese sentences and 8,775 functional expressions. Our scheme achieves high inter-annotator agreement with kappa score of 0.85. In the experiments, we confirmed that machine learning-based functional expression analysis contributes to factuality analysis.