Selection and Generation: Learning towards Multi-Product Advertisement Post Generation

30444

Authors

nan

Abstract

AbstractAs the E-commerce thrives, high-quality online advertising copywriting has attracted more and more attention. Different from the advertising copywriting for a single product, an advertisement (AD) post includes an attractive topic that meets the customer needs and description copywriting about several products under its topic. A good AD post can highlight the characteristics of each product, thus helps customers make a good choice among candidate products. Hence, multi-product AD post generation is meaningful and important. We propose a novel end-to-end model named S-MG Net to generate the AD post. Targeted at such a challenging real-world problem, we split the AD post generation task into two subprocesses: (1) select a set of products via the SelectNet (Selection Network). (2) generate a post including selected products via the MGenNet (Multi-Generator Network). Concretely, SelectNet first captures the post topic and the relationship among the products to output the representative products. Then, MGenNet generates the description copywriting of each product. Experiments conducted on a large-scale real-world AD post dataset demonstrate that our proposed model achieves impressive performance in terms of both automatic metrics as well as human evaluations.

Keywords

nan

Full Content

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 3818–3829, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 3818 Selection and Generation: Learning towards Multi-Product Advertisement Post Generation Zhangming Chan1,2,∗, Yuchi Zhang3, Xiuying Chen1,2, Shen Gao2, Zhiqiang Zhang3, Dongyan Zhao1,2 and Rui Yan1,2,† 1 Center for Data Science, AAIS, Peking University, Beijing, China 2 Wangxuan Institute of Computer Technology, Peking University, Beijing, China 3 Alibaba Group, Beijing, China {zhangming.chan,xy-chen,shengao,zhaody,ruiyan}@pku.edu.cn {yuchi.zyc,zhang.zhiqiang}@alibaba-inc.com Abstract As the E-commerce thrives, high-quality on- line advertising copywriting has attracted more and more attention. Different from the advertising copywriting for a single product, an advertisement (AD) post includes an attrac- tive topic that meets the customer needs and description copywriting about several products under its topic. A good AD post can highlight the characteristics of each product, thus helps customers make a good choice among candi- date products. Hence, multi-product AD post generation is meaningful and important. We propose a novel end-to-end model named S- MG Net to generate the AD post. Targeted at such a challenging real-world problem, we split the AD post generation task into two subprocesses: (1) select a set of products via the SelectNet (Selection Network). (2) gener- ate a post including selected products via the MGenNet (Multi-Generator Network). Con- cretely, SelectNet first captures the post topic and the relationship among the products to out- put the representative products. Then, MGen- Net generates the description copywriting of each product. Experiments conducted on a large-scale real-world AD post dataset demon- strate that our proposed model achieves im- pressive performance in terms of both auto- matic metrics as well as human evaluations. 1 Introduction With the fantastic development of the Internet, e- commerce has a rapid development and changes the customary shopping way of most people in the world. Advertising copywriting is a huge factor in e-commerce, and well-written advertising copy- writing can encourage consumers to understand further and purchase products. However, there is ∗ This work was done while Z. Chan was an intern at Alibaba Group. Y. Zhang works at Ant Group now. †Corresponding Author: Rui Yan (ruiyan@pku.edu.cn). Six oatmeals which are popular now, let’s find the one is yummy but will not let you be fat. Kellogg’s Tasty Granola-Rose You’ll be showered with a rich fragrant of roses You’ll be showered with a rich fragrant of roses when you tear open a bag of this granola. It is a great snack on its own, and with its crispy, sweet taste, you’ll find it easy to finish a whole bag in one day. It also makes a delicious breakfast if you eat it with milk or yogurt, which will bring out the sweet smell of the roses even more. The granola also contains roses even more. The granola also contains fine desiccated coconut that adds a refreshing coconut flavor to the taste. However, this type of granola is high in both calories and sugar, so it’s probably not the best choice for those of you who are on a diet. …

Content truncated to 500 words

Labeled Text

AbstractAs the E-commerce thrives, high-quality online advertising copywriting has attracted more and more attention. Different from the advertising copywriting for a single product, an advertisement (AD) post includes an attractive topic that meets the customer needs and description copywriting about several products under its topic. A good AD post can highlight the characteristics of each product, thus helps customers make a good choice among candidate products. Hence, multi-product AD post generation is meaningful and important. We propose a novel end-to-end model named S-MG Net to generate the AD post. Targeted at such a challenging real-world problem, we split the AD post generation task into two subprocesses: (1) select a set of products via the SelectNet (Selection Network). (2) generate a post including selected products via the MGenNet (Multi-Generator Network). Concretely, SelectNet first captures the post topic and the relationship among the products to output the representative products. Then, MGenNet generates the description copywriting of each product. Experiments conducted on a large-scale real-world AD post dataset demonstrate that our proposed model achieves impressive performance in terms of both automatic metrics as well as human evaluations.

Publication Details

Paper ID:
30444
Year:
2020
Publication:
TIPSTER
Publication Type:
conf
DOI:
nan