We present a review of personality in neural conversational agents (CAs),
also called chatbots. First, we define Personality, Persona, and Profile. We
explain all personality schemes which have been used in CAs, and list models
under the scheme(s) which they use. Second we describe 21 datasets which have
been developed in recent CA personality research. Third, we define the methods
used to embody personality in a CA, and review recent models using them.
Fourth, we survey some relevant reviews on CAs, personality, and related
topics. Finally, we draw conclusions and identify some research challenges for
this important emerging field.

综述了神经会话代理（也称为聊天机器人）中的个性特征，包括定义了个性、角色和档案，解释了在会话代理中已经使用的所有个性方案，并列出了使用该方案的模型；描述了在最近的会话代理个性研究中开发的 21 个数据集；定义了在会话代理中体现个性的方法，并回顾了最近使用这些方法的模型；调查了关于会话代理、个性和相关主题的一些相关综述；最后得出结论并确定了这一重要新兴领域的一些研究挑战。

对于会话代理和聊天机器人中的个性、角色和简介的调查

A Survey of Personality, Persona, and Profile in Conversational Agents  and Chatbots

Prior studies addressing target-oriented conversational tasks lack a crucial
notion that has been intensively studied in the context of goal-oriented
artificial intelligence agents, namely, planning. In this study, we propose the
task of Target-Guided Open-Domain Conversation Planning (TGCP) task to evaluate
whether neural conversational agents have goal-oriented conversation planning
abilities. Using the TGCP task, we investigate the conversation planning
abilities of existing retrieval models and recent strong generative models. The
experimental results reveal the challenges facing current technology.

本研究提出 Target-Guided Open-Domain Conversation Planning（TGCP）任务，通过对现有的检索模型和最近的强生成模型进行实验验证发现，当前技术面临的挑战是缺少神经会话代理人的目标导向的对话规划能力。

目标导向的开放领域对话规划

Target-Guided Open-Domain Conversation Planning

Generating diverse, interesting responses to chitchat conversations is a
problem for neural conversational agents. This paper makes two substantial
contributions to improving diversity in dialogue generation. First, we propose
a novel metric which uses Natural Language Inference (NLI) to measure the
semantic diversity of a set of model responses for a conversation. We evaluate
this metric using an established framework (Tevet and Berant, 2021) and find
strong evidence indicating NLI Diversity is correlated with semantic diversity.
Specifically, we show that the contradiction relation is more useful than the
neutral relation for measuring this diversity and that incorporating the NLI
model's confidence achieves state-of-the-art results. Second, we demonstrate
how to iteratively improve the semantic diversity of a sampled set of responses
via a new generation procedure called Diversity Threshold Generation, which
results in an average 137% increase in NLI Diversity compared to standard
generation procedures.

本文通过提出一种新的度量方法和一种称为 Diversity Threshold Generation 的新生成程序来改进对话生成，从而在多样性方面取得了显著进展。