Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems

TL;DR

Entriever is an energy-based retrieval model that models the relevance of knowledge pieces collectively, significantly improving knowledge retrieval and dialog system performance in knowledge-grounded NLP tasks.

Contribution

The paper introduces Entriever, a novel energy-based retriever that models multiple knowledge pieces jointly, outperforming existing models in knowledge retrieval and dialog system tasks.

Findings

Entriever outperforms cross-encoder baselines in knowledge retrieval.

Entriever improves end-to-end performance of knowledge-grounded dialog systems.

Semi-supervised training with Entriever enhances knowledge scoring accuracy.

Abstract

A retriever, which retrieves relevant knowledge pieces from a knowledge base given a context, is an important component in many natural language processing (NLP) tasks. Retrievers have been introduced in knowledge-grounded dialog systems to improve knowledge acquisition. In knowledge-grounded dialog systems, when conditioning on a given context, there may be multiple relevant and correlated knowledge pieces. However, knowledge pieces are usually assumed to be conditionally independent in current retriever models. To address this issue, we propose Entriever, an energy-based retriever. Entriever directly models the candidate retrieval results as a whole instead of modeling the knowledge pieces separately, with the relevance score defined by an energy function. We explore various architectures of energy functions and different training methods for Entriever, and show that Entriever substantially outperforms the strong cross-encoder baseline in knowledge retrieval tasks. Furthermore, we show that in semi-supervised training of knowledge-grounded dialog systems, Entriever enables effective scoring of retrieved knowledge pieces and significantly improves end-to-end performance of dialog systems.