Product Title Generation for Conversational Systems using BERT

TL;DR

This paper introduces a BERT-based sequence-to-sequence model to generate concise, natural spoken language titles for products, improving voice interface interactions in e-commerce.

Contribution

It presents a novel application of BERT for product title summarization tailored for conversational systems, outperforming existing baseline models.

Findings

BERT-based summarization outperforms baseline models in experiments.

Human evaluation confirms improved naturalness and clarity.

Model effectively generates spoken language-friendly product titles.

Abstract

Through recent advancements in speech technology and introduction of smart devices, such as Amazon Alexa and Google Home, increasing number of users are interacting with applications through voice. E-commerce companies typically display short product titles on their webpages, either human-curated or algorithmically generated, when brevity is required, but these titles are dissimilar from natural spoken language. For example, "Lucky Charms Gluten Free Break-fast Cereal, 20.5 oz a box Lucky Charms Gluten Free" is acceptable to display on a webpage, but "a 20.5 ounce box of lucky charms gluten free cereal" is easier to comprehend over a conversational system. As compared to display devices, where images and detailed product information can be presented to users, short titles for products are necessary when interfacing with voice assistants. We propose a sequence-to-sequence approach using BERT to generate short, natural, spoken language titles from input web titles. Our extensive experiments on a real-world industry dataset and human evaluation of model outputs, demonstrate that BERT summarization outperforms comparable baseline models.