将统计假设检验集成到深度神经网络中
Towards Integration of Statistical Hypothesis Tests into Deep Neural Networks
摘要:
我们报告了我们正在进行的关于一个新的深度架构的工作,该架构与一个统计测试程序协同工作,用于联合训练文本及其标签描述,以实现多标签和多类分类任务。一个统计假设检验方法是用来提取最翔实的话,为每个给定的类。这些词被用作更具有标签意识的文本分类的类描述。直觉是帮助模型专注于信息量更大的单词,而不是更频繁的单词。该模型利用标签描述的使用,除了输入文本,以提高文本分类性能。我们的方法是完全数据驱动的,没有依赖于其他来源的信息比训练数据,并适应于不同的分类问题,通过提供适当的训练数据,而无需主要的超参数调整。我们在几个公开可用的数据集上训练和测试了我们的系统,在这些数据集上,我们成功地提高了一个高利润率数据集的最新技术水平,并在所有其他数据集上获得了有竞争力的结果。
英文摘要:
We report our ongoing work about a new deep architecture working in tandem with a statistical test procedure for jointly training texts and their label descriptions for multi-label and multi-class classification tasks. A statistical hypothesis testing method is used to extract the most informative words for each given class. These words are used as a class description for more label-aware text classification. Intuition is to help the model to concentrate on more informative words rather than more frequent ones. The model leverages the use of label descriptions in addition to the input text to enhance text classification performance. Our method is entirely data-driven, has no dependency on other sources of information than the training data, and is adaptable to different classification problems by providing appropriate training data without major hyper-parameter tuning. We trained and tested our system on several publicly available datasets, where we managed to improve the state-of-the-art on one set with a high margin, and to obtain competitive results on all other ones.
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。