论文标题
没有刺就没有玫瑰:就模型,数据和以用户为中心的方法而言,在Blenderbot 2.0上找到弱点
There is no rose without a thorn: Finding weaknesses on BlenderBot 2.0 in terms of Model, Data and User-Centric Approach
论文作者
论文摘要
Blenderbot 2.0是一个对话模型,它通过使用Internet搜索模块和多主题来反映实时信息并记住长时间的用户信息来代表开放域聊天机器人。尽管如此,该模型仍然有改进的余地。为此,我们从三个角度检查了Blenderbot 2.0限制和错误:模型,数据和用户。从数据的角度来看,我们强调了在众包过程中向工人提供的不清楚指南,以及缺乏在收集的数据中完善仇恨言论的过程并验证基于Internet的信息的准确性。从用户的角度来看,我们确定了Blenderbot 2.0的九种类型的局限性,并对它们的原因进行了彻底的研究。此外,对于每种观点,我们提出了实际的改进方法,并讨论了一些潜在的未来研究方向。
BlenderBot 2.0 is a dialogue model that represents open-domain chatbots by reflecting real-time information and remembering user information for an extended period using an internet search module and multi-session. Nonetheless, the model still has room for improvement. To this end, we examine BlenderBot 2.0 limitations and errors from three perspectives: model, data, and user. From the data point of view, we highlight the unclear guidelines provided to workers during the crowdsourcing process, as well as a lack of a process for refining hate speech in the collected data and verifying the accuracy of internet-based information. From a user perspective, we identify nine types of limitations of BlenderBot 2.0, and their causes are thoroughly investigated. Furthermore, for each point of view, we propose practical improvement methods and discuss several potential future research directions.