论文标题
预训练的语言模型是否知识渊博，可以实现地面开放式域对话？
Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues?
论文作者
论文摘要
我们使用预先训练的语言模型研究知识接地的对话生成。我们试图了解存储在预训练模型的参数中的知识是否已经足以接地开放域对话，从而使我们能够摆脱一代中对外部知识源的依赖，而不是在基准上追求新的最先进的基准。通过对基准测试的广泛实验，我们发现，通过对包含知识的一些对话进行微调，预训练的语言模型可以胜过最先进的模型，该模型需要自动评估和人类判断中的外部知识，这对我们提出的问题提出了积极的答案。
We study knowledge-grounded dialogue generation with pre-trained language models. Instead of pursuing new state-of-the-art on benchmarks, we try to understand if the knowledge stored in parameters of the pre-trained models is already enough to ground open domain dialogues, and thus allows us to get rid of the dependency on external knowledge sources in generation. Through extensive experiments on benchmarks, we find that by fine-tuning with a few dialogues containing knowledge, the pre-trained language models can outperform the state-of-the-art model that requires external knowledge in automatic evaluation and human judgment, suggesting a positive answer to the question we raised.
