Ranking sentences from product description & bullets for better search

TL;DR

This paper proposes reinforcement learning methods to rank sentences in product descriptions and bullets, improving search relevance and attribute extraction by focusing on the most informative sentences.

Contribution

It introduces two novel extractive summarization models leveraging product titles and click logs for sentence ranking in ecommerce product fields.

Findings

The models outperform baseline methods in sentence relevance.

Leveraging click logs improves ranking accuracy.

Enhanced sentence selection aids better search and attribute extraction.

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.