Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference

TL;DR

This paper introduces Sequential Posterior Inference (SPI), an end-to-end framework for knowledge-grounded dialogue generation that improves diversity and faithfulness without relying on inference networks.

Contribution

SPI is a novel end-to-end learning method that samples from the posterior distribution for knowledge selection and response generation, avoiding the need for inference networks.

Findings

SPI outperforms previous methods on Wizard of Wikipedia and Holl-E datasets.

SPI achieves higher automatic evaluation scores.

Human evaluations favor SPI's responses for faithfulness and diversity.

Abstract

The capability to generate responses with diversity and faithfulness using factual knowledge is paramount for creating a human-like, trustworthy dialogue system. Common strategies either adopt a two-step paradigm, which optimizes knowledge selection and response generation separately, and may overlook the inherent correlation between these two tasks, or leverage conditional variational method to jointly optimize knowledge selection and response generation by employing an inference network. In this paper, we present an end-to-end learning framework, termed Sequential Posterior Inference (SPI), capable of selecting knowledge and generating dialogues by approximately sampling from the posterior distribution. Unlike other methods, SPI does not require the inference network or assume a simple geometry of the posterior distribution. This straightforward and intuitive inference procedure of SPI directly queries the response generation model, allowing for accurate knowledge selection and generation of faithful responses. In addition to modeling contributions, our experimental results on two common dialogue datasets (Wizard of Wikipedia and Holl-E) demonstrate that SPI outperforms previous strong baselines according to both automatic and human evaluation metrics.