Product Title Refinement via Multi-Modal Generative Adversarial Learning

Abstract

Nowadays, an increasing number of customers are in favor of using E-commerce Apps to browse and purchase products. Since merchants are usually inclined to employ redundant and over-informative product titles to attract customers' attention, it is of great importance to concisely display short product titles on limited screen of cell phones. Previous researchers mainly consider textual information of long product titles and lack of human-like view during training and evaluation procedure. In this paper, we propose a Multi-Modal Generative Adversarial Network (MM-GAN) for short product title generation, which innovatively incorporates image information, attribute tags from the product and the textual information from original long titles. MM-GAN treats short titles generation as a reinforcement learning process, where the generated titles are evaluated by the discriminator in a human-like view.

arXiv commentWorkshop on Visually Grounded Interaction and Language, NIPS, 2018

References in corpus (7)

• Sequence to Sequence Learning with Neural Networks
• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
• Adversarial Learning for Neural Dialogue Generation
• AttSum: Joint Learning of Focusing and Summarization with Neural Attention
• Distraction-Based Neural Networks for Document Summarization
• Data Generation as Sequential Decision Making
• Automatic Generation of Chinese Short Product Titles for Mobile Display

Cited by in corpus (2)

• Discriminative Pre-training for Low Resource Title Compression in Conversational Grocery
• Unsupervised Meta Learning for One Shot Title Compression in Voice Commerce