arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.06246cs.CV
收藏

SuperTML:结构化表格数据预测的二维的词嵌入

SuperTML: Two-Dimensional Word Embedding for the Precognition on Structured Tabular Data

Gyrfalcon Technology Inc.(矛隼科技公司)

Baohua Sun, Lin Yang, Wenhan Zhang, Michael Lin, Patrick Dong, Charles Young, Jason Dong

摘要:

表格数据是工业中最常用的数据形式。梯度提升树、支持向量机、随机森林和逻辑回归通常用于表格数据的分类任务。使用分类嵌入的DNN模型也应用于此任务,但迄今为止所有尝试都使用一维嵌入。最近的工作超级字符的方法,使用二维的【形】词嵌入在文本分类任务中取得了最先进的结果,展示了这种新方法的承诺。在本文中,我们提出了SuperTML方法,它借用了超级字符方法和二维的【形】嵌入的思想来解决表格数据的分类问题。对于表格数据的每个输入,特征首先被投影到像图像一样的二维的【形】嵌入中,然后将该图像馈送到微调的二维的【形】CNN模型中进行分类。实验结果表明,所提出的SuperTML方法在大型和小型数据集上都取得了最先进的结果。

英文摘要:

Tabular data is the most commonly used form of data in industry. Gradient Boosting Trees, Support Vector Machine, Random Forest, and Logistic Regression are typically used for classification tasks on tabular data. DNN models using categorical embeddings are also applied in this task, but all attempts thus far have used one-dimensional embeddings. The recent work of Super Characters method using two-dimensional word embeddings achieved the state of art result in text classification tasks, showcasing the promise of this new approach. In this paper, we propose the SuperTML method, which borrows the idea of Super Characters method and two-dimensional embeddings to address the problem of classification on tabular data. For each input of tabular data, the features are first projected into two-dimensional embeddings like an image, and then this image is fed into fine-tuned two-dimensional CNN models for classification. Experimental results have shown that the proposed SuperTML method had achieved state-of-the-art results on both large and small datasets.

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。

↑