Counterfactual data augmentation via perspective transition for open-domain dialogues

J Ou, J Zhang, Y Feng, J Zhou - arxiv preprint arxiv:2210.16838, 2022 - arxiv.org
The construction of open-domain dialogue systems requires high-quality dialogue datasets.
The dialogue data admits a wide variety of responses for a given dialogue history, especially …

Partner personas generation for dialogue response generation

H Lu, W Lam, H Cheng, H Meng - … of the 2022 Conference of the …, 2022 - aclanthology.org
Incorporating personas information allows diverse and engaging responses in dialogue
response generation. Unfortunately, prior works have primarily focused on self personas …

State-of-the-art in Open-domain Conversational AI: A Survey

T Adewumi, F Liwicki, M Liwicki - Information, 2022 - mdpi.com
We survey SoTA open-domain conversational AI models with the objective of presenting the
prevailing challenges that still exist to spur future research. In addition, we provide statistics …

An equal-size hard EM algorithm for diverse dialogue generation

Y Wen, Y Hao, Y Cao, L Mou - arxiv preprint arxiv:2209.14627, 2022 - arxiv.org
Open-domain dialogue systems aim to interact with humans through natural language texts
in an open-ended fashion. Despite the recent success of super large dialogue systems such …

SimOAP: Improve coherence and consistency in persona-based dialogue generation via over-sampling and post-evaluation

J Zhou, L Pang, H Shen, X Cheng - arxiv preprint arxiv:2305.11130, 2023 - arxiv.org
Language models trained on large-scale corpora can generate remarkably fluent results in
open-domain dialogue. However, for the persona-based dialogue generation task …