×
In this study, we build a dialogue system that can respond based on a given character setting (persona) to bring consistency. Considering the trend of the ...
Jun 11, 2022 · In this study, we build a dialogue system that can respond based on a given character setting (persona) to bring consistency. Considering the ...
Jul 10, 2022 · In this study, we build a dialogue system that can respond based on a given character setting (persona) to bring con- sistency. Considering the ...
People also ask
Sep 22, 2024 · In this study, we build a dialogue system that can respond based on a given character setting (persona) to bring consistency. Considering the ...
Paper reading list in Conversational AI, mainly encompassing dialogue systems and natural language generation. This repository is constantly updating.
Oct 17, 2023 · Exploring Automatic Evaluation Methods based on a Decoder-based LLM for Text Generation · Building a Personalized Dialogue System with Prompt- ...
NAACL22 Building a Personalized Dialogue System with Prompt-Tuning, 2022. ... ACL19 Persuasion for good: Towards a personalized persuasive dialogue system for ...
If we naively concurrently tune all prompts without clear distinctions, this would yield only marginal differences compared with tuning one soft prompt.
1In our study, we utilized prefix-tuning. However, Person-. aPKT can be adapted to any of the parameter-efficient tuning approaches, such as prompt-tuning.
'w/o. CL', 'w/o FUSION', and 'w/o SL' denote no context- prompt contrastive loss, no prompt fusion learning loss, and no prompt selection loss, respectively.