Improving Automatic Sentence-Level Annotation of Human Values Using Augmented Feature Vectors
Improving Automatic Sentence-Level Annotation of Human Values Using Augmented Feature Vectors
复制标题
DOI：
--
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Yasuhiro Takayama;Yoichi Tomiura;Emi Ishita;Zheng Wang;Douglas W. Oard;K. Fleischmann;An-Shou Cheng
中科院分区：
文献类型：
--
作者：
Yasuhiro Takayama;Yoichi Tomiura;Emi Ishita;Zheng Wang;Douglas W. Oard;K. Fleischmann;An-Shou Cheng
本文件介绍了一项努力，以改善识别的人的价值观，直接或间接援引的证人在立法和监管听证会前准备的陈述。我们使用监督机器学习技术在几千个带注释的句子上训练，在句子级别自动编码人类价值。为了模拟实际情况，我们将四分之一的数据作为标记用于训练，其余四分之三的数据作为未标记用于测试。我们发现，使用词汇和统计共现证据的组合来增强特征空间，可以产生约6%的相对改善F1使用支持向量机分类器。
This paper describes an effort to improve identification of human values that are directly or indirectly invoked within the prepared statements of witnesses before legislative and regulatory hearings. We automatically code human values at the sentence level using supervised machine learning techniques trained on a few thousand annotated sentences. To simulate an actual situation, we treat a quarter of the data as labeled for training and the remaining three quarters of the data as unlabeled for test. We find that augmenting the feature space using a combination of lexical and statistical co-occurrence evidence can yield about a 6% relative improvement in F 1 using a Support Vector Machine classifier.