Ranking sentences from product description & bullets for better search
This work addresses search optimization for ecommerce platforms, but it appears incremental as it builds on existing summarization and reinforcement learning techniques.
The paper tackled the problem of verbose product descriptions and bullets in ecommerce catalogs, which can hinder search relevance and attribute extraction, by developing two methods based on extractive summarization with reinforcement learning to rank sentences, resulting in a comparison of their accuracy.
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.