Temporal-based feature selection and transfer learning for text categorization
Temporal-based feature selection and transfer learning for text categorization
复制标题
DOI：
10.5220/0005593100170026
复制
发表时间：
2015-11
期刊：
影响因子：
--
通讯作者：
Fumiyo Fukumoto;Yoshimi Suzuki
中科院分区：
文献类型：
--
作者：
Fumiyo Fukumoto;Yoshimi Suzuki
本文解决了训练数据与测试数据可能来自不同时间段的文本分类问题。我们提出了一种最小化时间效应影响的文本分类方法。与之前的文本分类工作一样，我们使用了特征选择。根据语料库统计，我们选择了两种类型的信息术语。一个是与时间无关的术语，这些术语在训练文档的整个时间范围内都很突出。另一个是与时间相关的术语，它们在特定的时间段内很重要。对于由独立/相关项表示的训练文档，我们采用基于增强的迁移学习来学习精确的时间轴适应模型。使用日本数据的结果表明，该方法与目前最先进的bias - svm方法相当，我们的方法获得的宏观平均f分数为0.688，bias - svm的宏观平均f分数为0.671。此外，我们发现该方法是有效的，特别是当测试数据的创建时间周期与训练数据的创建时间周期相差很大时。
This paper addresses text categorization problem that training data may derive from a different time period from the test data. We present a method for text categorization that minimizes the impact of temporal effects. Like much previous work on text categorization, we used feature selection. We selected two types of informative terms according to corpus statistics. One is temporal independent terms that are salient across full temporal range of training documents. Another is temporal dependent terms which are important for a specific time period. For the training documents represented by independent/dependent terms, we applied boosting based transfer learning to learn accurate model for timeline adaptation. The results using Japanese data showed that the method was comparable to the current state-of-the-art biased-SVM method, as the macro-averaged F-score obtained by our method was 0.688 and that of biased-SVM was 0.671. Moreover, we found that the method is effective, especially when the creation time period of the test data differs greatly from that of the training data.