论文标题
迈向基于立场的角色进行对话
Toward Stance-based Personas for Opinionated Dialogues
论文作者
论文摘要
在Chit-Chat对话的背景下,已经表明,具有角色配置文件的赋予系统对于产生更连贯和有意义的对话很重要。尽管如此,到目前为止,这种角色的表现仅限于基于事实的表示(例如“我有两只猫”)。我们认为这些表示仍然是表面的W.R.T.人格的复杂性。在这项工作中,我们建议迈出一步,并研究基于立场的角色,试图掌握更深刻的特征,例如观点,价值观和信念,以推动语言产生。为此,我们介绍了一个新颖的数据集,允许探索基于立场的角色表征及其对索赔产生的影响,表明他们能够掌握作者角色的抽象和深刻方面。
In the context of chit-chat dialogues it has been shown that endowing systems with a persona profile is important to produce more coherent and meaningful conversations. Still, the representation of such personas has thus far been limited to a fact-based representation (e.g. "I have two cats."). We argue that these representations remain superficial w.r.t. the complexity of human personality. In this work, we propose to make a step forward and investigate stance-based persona, trying to grasp more profound characteristics, such as opinions, values, and beliefs to drive language generation. To this end, we introduce a novel dataset allowing to explore different stance-based persona representations and their impact on claim generation, showing that they are able to grasp abstract and profound aspects of the author persona.