arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.07545cs.CLstat.ML
收藏

交互式语义特征文本分类

Interactive Semantic Featuring for Text Classification

Microsoft Research(微软研究院);Facebook AI Research(脸书人工智能研究院)

Camille Jandot, Patrice Simard, Max Chickering, David Grangier, Jina Suh

摘要:

在文本分类中,词典可以用来定义人类可理解的特征。我们提出了一种改进的字典功能称为平滑字典功能。这些特征识别文档上下文而不是n-gram。我们描述了一个原则性的方法,征求字典功能的教师,目前的结果表明,使用这些人类可理解的功能建立的模型是有竞争力的模型训练的词袋功能。

英文摘要:

In text classification, dictionaries can be used to define human-comprehensible features. We propose an improvement to dictionary features called smoothed dictionary features. These features recognize document contexts instead of n-grams. We describe a principled methodology to solicit dictionary features from a teacher, and present results showing that models built using these human-comprehensible features are competitive with models trained with Bag of Words features.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑