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

Yan Xu, Deqian Kong, Dehong Xu, Ziwei Ji, Bo Pang, Pascale Fung, Ying Nian Wu
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38518-38534, 2023.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-xu23j, title = {Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference}, author = {Xu, Yan and Kong, Deqian and Xu, Dehong and Ji, Ziwei and Pang, Bo and Fung, Pascale and Wu, Ying Nian}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {38518--38534}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/xu23j/xu23j.pdf}, url = {https://proceedings.mlr.press/v202/xu23j.html}, 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.} }
Endnote
%0 Conference Paper %T Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference %A Yan Xu %A Deqian Kong %A Dehong Xu %A Ziwei Ji %A Bo Pang %A Pascale Fung %A Ying Nian Wu %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-xu23j %I PMLR %P 38518--38534 %U https://proceedings.mlr.press/v202/xu23j.html %V 202 %X 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.
APA
Xu, Y., Kong, D., Xu, D., Ji, Z., Pang, B., Fung, P. & Wu, Y.N.. (2023). Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:38518-38534 Available from https://proceedings.mlr.press/v202/xu23j.html.

Related Material