Fast and Light-Weight Answer Text Retrieval in Dialogue Systems

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...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Wan, Hui, Patel, Siva Sankalp, Murdock, J William, Potdar, Saloni, Joshi, Sachindra
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 31.05.2022
Subjects
Interactive computer systems
Retrieval
System effectiveness
Weight reduction
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422