A survey of knowledge-enhanced text generation

W Yu, C Zhu, Z Li, Z Hu, Q Wang, H Ji… - ACM Computing …, 2022‏ - dl.acm.org
The goal of text-to-text generation is to make machines express like a human in many
applications such as conversation, summarization, and translation. It is one of the most …

BoB: BERT over BERT for training persona-based dialogue models from limited personalized data

H Song, Y Wang, K Zhang, WN Zhang, T Liu - arxiv preprint arxiv …, 2021‏ - arxiv.org
Maintaining consistent personas is essential for dialogue agents. Although tremendous
advancements have been brought, the limited-scale of annotated persona-dense data are …

You impress me: Dialogue generation via mutual persona perception

Q Liu, Y Chen, B Chen, JG Lou, Z Chen, B Zhou… - arxiv preprint arxiv …, 2020‏ - arxiv.org
Despite the continuing efforts to improve the engagingness and consistency of chit-chat
dialogue systems, the majority of current work simply focus on mimicking human-like …

A pre-training based personalized dialogue generation model with persona-sparse data

Y Zheng, R Zhang, M Huang, X Mao - Proceedings of the AAAI …, 2020‏ - ojs.aaai.org
Endowing dialogue systems with personas is essential to deliver more human-like
conversations. However, this problem is still far from well explored due to the difficulties of …

Persona-based conversational ai: State of the art and challenges

J Liu, C Symons, RR Vatsavai - 2022 IEEE International …, 2022‏ - ieeexplore.ieee.org
Conversational AI has become an increasingly prominent and practical application of
machine learning. How-ever, existing conversational AI techniques still suffer from var-ious …

One chatbot per person: Creating personalized chatbots based on implicit user profiles

Z Ma, Z Dou, Y Zhu, H Zhong, JR Wen - Proceedings of the 44th …, 2021‏ - dl.acm.org
Personalized chatbots focus on endowing chatbots with a consistent personality to behave
like real users, give more informative responses, and further act as personal assistants …

Writer-defined AI personas for on-demand feedback generation

K Benharrak, T Zindulka, F Lehmann, H Heuer… - Proceedings of the …, 2024‏ - dl.acm.org
Compelling writing is tailored to its audience. This is challenging, as writers may struggle to
empathize with readers, get feedback in time, or gain access to the target group. We …

Less is more: Learning to refine dialogue history for personalized dialogue generation

H Zhong, Z Dou, Y Zhu, H Qian, JR Wen - arxiv preprint arxiv:2204.08128, 2022‏ - arxiv.org
Personalized dialogue systems explore the problem of generating responses that are
consistent with the user's personality, which has raised much attention in recent years …

Generate, delete and rewrite: A three-stage framework for improving persona consistency of dialogue generation

H Song, Y Wang, WN Zhang, X Liu, T Liu - arxiv preprint arxiv:2004.07672, 2020‏ - arxiv.org
Maintaining a consistent personality in conversations is quite natural for human beings, but
is still a non-trivial task for machines. The persona-based dialogue generation task is thus …

Like hiking? you probably enjoy nature: Persona-grounded dialog with commonsense expansions

BP Majumder, H Jhamtani, T Berg-Kirkpatrick… - arxiv preprint arxiv …, 2020‏ - arxiv.org
Existing persona-grounded dialog models often fail to capture simple implications of given
persona descriptions, something which humans are able to do seamlessly. For example …