Probing Product Description Generation via Posterior Distillation

03/02/2021
by   Haolan Zhan, et al.
0

In product description generation (PDG), the user-cared aspect is critical for the recommendation system, which can not only improve user's experiences but also obtain more clicks. High-quality customer reviews can be considered as an ideal source to mine user-cared aspects. However, in reality, a large number of new products (known as long-tailed commodities) cannot gather sufficient amount of customer reviews, which brings a big challenge in the product description generation task. Existing works tend to generate the product description solely based on item information, i.e., product attributes or title words, which leads to tedious contents and cannot attract customers effectively. To tackle this problem, we propose an adaptive posterior network based on Transformer architecture that can utilize user-cared information from customer reviews. Specifically, we first extend the self-attentive Transformer encoder to encode product titles and attributes. Then, we apply an adaptive posterior distillation module to utilize useful review information, which integrates user-cared aspects to the generation process. Finally, we apply a Transformer-based decoding phase with copy mechanism to automatically generate the product description. Besides, we also collect a large-scare Chinese product description dataset to support our work and further research in this field. Experimental results show that our model is superior to traditional generative models in both automatic indicators and human evaluation.

READ FULL TEXT
research
02/16/2021

User-Inspired Posterior Network for Recommendation Reason Generation

Recommendation reason generation, aiming at showing the selling points o...
research
11/11/2018

Attentive Aspect Modeling for Review-aware Recommendation

In recent years, many studies extract aspects from user reviews and inte...
research
04/14/2022

Latent Aspect Detection from Online Unsolicited Customer Reviews

Within the context of review analytics, aspects are the features of prod...
research
04/20/2020

A Review-based Transformer Model for Personalized Product Search

In product search, customers make purchase decisions based on not only t...
research
09/10/2019

Learning review representations from user and product level information for spam detection

Opinion spam has become a widespread problem in social media, where hire...
research
03/29/2019

Towards Knowledge-Based Personalized Product Description Generation in E-commerce

Quality product descriptions are critical for providing competitive cust...
research
09/20/2022

Generating Persuasive Responses to Customer Reviews with Multi-Source Prior Knowledge in E-commerce

Customer reviews usually contain much information about one's online sho...

Please sign up or login with your details

Forgot password? Click here to reset