Fast and Light-Weight Answer Text Retrieval in Dialogue Systems
This work addresses the problem of high computational costs for deploying advanced retrieval systems in industrial-scale dialogue services, offering a practical improvement for cloud-based applications.
The paper tackled the challenge of scaling neural dense retrieval for dialogue systems by developing a fast and cost-efficient solution that operates effectively on inexpensive hardware, showing competitive performance compared to leading industrial alternatives.
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.