Ranking sentences from product description & bullets for better search

Abstract

Products in an ecommerce catalog contain information-rich fields like description and bullets that can be useful to extract entities (attributes) using NER based systems. However, these fields are often verbose and contain lot of information that is not relevant from a search perspective. Treating each sentence within these fields equally can lead to poor full text match and introduce problems in extracting attributes to develop ontologies, semantic search etc. To address this issue, we describe two methods based on extractive summarization with reinforcement learning by leveraging information in product titles and search click through logs to rank sentences from bullets, description, etc. Finally, we compare the accuracy of these two models.

arXiv commentAccepted at SIGIR eCom'19

References in corpus (11)

• A Deep Reinforced Model for Abstractive Summarization
• Sequence Level Training with Recurrent Neural Networks
• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
• Deep Reinforcement Learning for Dialogue Generation
• Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
• A Hierarchical Neural Autoencoder for Paragraphs and Documents
• Neural Summarization by Extracting Sentences and Words
• Neural Extractive Summarization with Side Information
• Distraction-Based Neural Networks for Document Summarization
• Graph-based Neural Multi-Document Summarization
• Towards a simplified ontology for better e-commerce search