Multi-Source Pointer Network for Product Title Summarization

Abstract

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.

arXiv comment10 pages, To appear in CIKM 2018, fix mistakes in dataset stats

References in corpus (11)

• Sequence to Sequence Learning with Neural Networks
• On the difficulty of training Recurrent Neural Networks
• A Deep Reinforced Model for Abstractive Summarization
• Pointer Sentinel Mixture Models
• Topic Aware Neural Response Generation
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• Neural Summarization by Extracting Sentences and Words
• Latent Predictor Networks for Code Generation
• Pointing the Unknown Words
• Language as a Latent Variable: Discrete Generative Models for Sentence Compression
• A Multi-task Learning Approach for Improving Product Title Compression with User Search Log Data