arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.04713cs.IR
收藏

利用主题建模增强知识检索以实现知识 grounded 对话

Enhancing Knowledge Retrieval with Topic Modeling for Knowledge-Grounded Dialogue

Nhat Tran, Diane Litman

AI总结:

本文提出在知识库上引入主题建模以增强神经检索,并结合 ChatGPT 利用改进后的检索结果提升知识 grounded 对话的回复生成,实验证明检索与生成性能均获提升。

摘要:

知识检索是构建知识 grounded 对话系统的主要挑战之一。一种常用方法是使用神经检索器配合分布式近似最近邻数据库,以快速查找相关知识句子。在本研究中,我们提出一种在知识库上利用主题建模的方法,以进一步提高检索准确率,从而改进回复生成。此外,我们还利用大型语言模型 ChatGPT 进行实验,借助提升后的检索性能进一步改善生成结果。在两个数据集上的实验结果表明,我们的方法能够提升检索和生成性能。结果还表明,当提供相关知识时,ChatGPT 是知识 grounded 对话中更优的回复生成器。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑