Online shopping has become more and more popular in recent years, which leads to a prosperity on online platforms. Generally, the identical products are provided by many sellers on multiple platforms. Thus the comparison between products on multiple platforms becomes a basic demand for both consumers and sellers. However, identifying identical products on multiple platforms is difficult because the description for a certain product can be various. In this work, we propose a novel neural matching model to solve this problem. Two kinds of descriptions (i.e. product titles and attributes), which are widely provided on online platforms, are considered in our method. We conduct experiments on a real-world data set which contains thousands of products on two online e-commerce platforms. The experimental results show that our method can take use of the product information contained in both titles and attributes and significantly outperform the state-of-the-art matching models.

中文翻译：

---

电子商务中的深跨平台产品匹配

近年来，在线购物变得越来越流行，这导致在线平台上的繁荣。通常，许多卖家在多个平台上提供相同的产品。因此，多个平台上的产品之间的比较成为消费者和卖方的基本需求。但是，由于多个产品的描述可能不同，因此在多个平台上识别相同的产品非常困难。在这项工作中，我们提出了一种新颖的神经匹配模型来解决这个问题。我们的方法考虑了在线平台上广泛提供的两种描述（即产品标题和属性）。我们在一个包含两个在线电子商务平台上数千种产品的真实数据集上进行实验。