Fast and Light-Weight Answer Text Retrieval in Dialogue Systems

TL;DR

This paper introduces a fast, lightweight neural answer text retrieval method for dialogue systems that operates efficiently on inexpensive hardware, making advanced retrieval scalable and cost-effective for industrial applications.

Contribution

It presents a novel neural retrieval approach optimized for speed and cost-efficiency, suitable for large-scale industrial dialogue systems.

Findings

Effective retrieval comparable to state-of-the-art models

Significantly faster and more cost-efficient

Operates well on inexpensive hardware

Abstract

Dialogue systems can benefit from being able to search through a corpus of text to find information relevant to user requests, especially when encountering a request for which no manually curated response is available. The state-of-the-art technology for neural dense retrieval or re-ranking involves deep learning models with hundreds of millions of parameters. However, it is difficult and expensive to get such models to operate at an industrial scale, especially for cloud services that often need to support a big number of individually customized dialogue systems, each with its own text corpus. We report our work on enabling advanced neural dense retrieval systems to operate effectively at scale on relatively inexpensive hardware. We compare with leading alternative industrial solutions and show that we can provide a solution that is effective, fast, and cost-efficient.