Multi-Source Pointer Network for Product Title Summarization
Multi-Source Pointer Network for Product Title Summarization
复制标题
DOI：
10.1145/3269206.3271722
复制
发表时间：
2018-08
期刊：
影响因子：
--
通讯作者：
Fei Sun;Peng Jiang;Hanxiao Sun;Changhua Pei;Wenwu Ou;Xiaobo Wang
中科院分区：
文献类型：
--
作者：
Fei Sun;Peng Jiang;Hanxiao Sun;Changhua Pei;Wenwu Ou;Xiaobo Wang
在本文中，我们研究了电子商务应用中的产品标题摘要问题，以显示在移动的设备上。与传统的句子摘要相比，产品标题摘要具有一些额外的和本质的限制。例如，事实错误或关键信息的丢失对于电子商务应用程序是不可容忍的。因此，我们为产品标题摘要抽象了另外两个约束：（i）不引入无关信息;（ii）保留关键信息（例如，品牌名称和商品名称）。为了解决这些问题，我们提出了一种新的多源指针网络，通过添加一个新的知识编码器的指针网络。第一个约束由指针机制处理。对于第二个约束，我们通过软门控机制从知识编码器中复制单词来恢复关键信息。为了进行评估，我们构建了大量真实世界的产品标题以及人类编写的简短标题沿着。实验结果表明，我们的模型显着优于其他基线。最后，我们提出的模型的在线部署产生了重大的业务影响，通过点击率来衡量。
In this paper, we study the product title summarization problem in E-commerce applications for display on mobile devices. Comparing with conventional sentence summarization, product title summarization has some extra and essential constraints. For example, factual errors or loss of the key information are intolerable for E-commerce applications. Therefore, we abstract two more constraints for product title summarization: (i) do not introduce irrelevant information; (ii) retain the key information (e.g., brand name and commodity name). To address these issues, we propose a novel multi-source pointer network by adding a new knowledge encoder for pointer network. The first constraint is handled by pointer mechanism. For the second constraint, we restore the key information by copying words from the knowledge encoder with the help of the soft gating mechanism. For evaluation, we build a large collection of real-world product titles along with human-written short titles. Experimental results demonstrate that our model significantly outperforms the other baselines. Finally, online deployment of our proposed model has yielded a significant business impact, as measured by the click-through rate.