Enhancing Knowledge Retrieval with Topic Modeling for Knowledge-Grounded Dialogue

TL;DR

This paper introduces a method that uses topic modeling to enhance knowledge retrieval in dialogue systems, leading to better response quality, and demonstrates that ChatGPT benefits from improved retrieval for more accurate responses.

Contribution

The paper proposes integrating topic modeling into knowledge retrieval for dialogue systems and evaluates its effectiveness with ChatGPT, showing improved retrieval and response quality.

Findings

Enhanced retrieval accuracy with topic modeling.

Improved response generation when using better knowledge retrieval.

ChatGPT performs better with relevant knowledge retrieved.

Abstract

Knowledge retrieval is one of the major challenges in building a knowledge-grounded dialogue system. A common method is to use a neural retriever with a distributed approximate nearest-neighbor database to quickly find the relevant knowledge sentences. In this work, we propose an approach that utilizes topic modeling on the knowledge base to further improve retrieval accuracy and as a result, improve response generation. Additionally, we experiment with a large language model, ChatGPT, to take advantage of the improved retrieval performance to further improve the generation results. Experimental results on two datasets show that our approach can increase retrieval and generation performance. The results also indicate that ChatGPT is a better response generator for knowledge-grounded dialogue when relevant knowledge is provided.