Implicit knowledge, such as common sense, is key to fluid human conversations. Current neural response generation (RG) models are trained to generate responses directly, omitting unstated implicit knowledge. In this paper, we present Think-Before-Speaking (TBS), a generative approach to first externalize implicit commonsense knowledge (think) and use this knowledge to generate responses (speak). We expect that externalizing implicit knowledge allows more efficient learning, produces more informative responses, and enables more explainable models. We analyze different choices to collect knowledge-aligned dialogues, represent implicit knowledge, and transition between knowledge and dialogues. Empirical results show TBS models outperform end-to-end and knowledge-augmented RG baselines on most automatic metrics and generate more informative, specific, and commonsense-following responses, as evaluated by human annotators. TBS also generates knowledge that makes sense and is relevant to the dialogue around 85\% of the time.
翻译:普通知识等隐含知识是人类对话流动的关键。 当前的神经反应生成模型( RG) 被培训直接产生反应, 省略不言而喻的隐含知识。 在本文中, 我们提出“ 思想- 未来” (TBS), 这是一种将隐含的普通知识(思维)首先外部化的基因化方法, 并利用这种知识来产生反应( Speak ) 。 我们期望, 将隐含的知识外部化可以更有效地学习, 产生更多信息化的响应, 并促成更可解释的模式。 我们分析不同的选择, 收集知识匹配的对话, 代表隐含的知识, 以及知识和对话之间的过渡。 经验性结果显示, TBS 模型在大多数自动指标上超越了终端至终端和知识强化的 RG基线, 并产生更多信息、 具体和常见的响应, 正如人类警告者所评价的那样。 TBS 也生成了有意义和与时约85 对话相关的知识。