Large-scale sequence-to-sequence models have shown to be adept at both multiple-choice and open-domain commonsense reasoning tasks. However, the current systems do not provide the ability to control the various attributes of the reasoning chain. To enable better controllability, we propose to study the commonsense reasoning as a template filling task (TemplateCSR) -- where the language models fills reasoning templates with the given constraints as control factors. As an approach to TemplateCSR, we (i) propose a dataset of commonsense reasoning template-expansion pairs and (ii) introduce POTTER, a pretrained sequence-to-sequence model using prompts to perform commonsense reasoning across concepts. Our experiments show that our approach outperforms baselines both in generation metrics and factuality metrics. We also present a detailed error analysis on our approach's ability to reliably perform commonsense reasoning.
翻译:大型序列到序列模型已经表明,在多重选择和开放的常见推理任务中,大尺度的序列到序列模型都非常适合。然而,目前的系统无法提供控制推理链各个属性的能力。为了更好地控制,我们提议研究常识推理,将其作为一个模板填充任务(TemplateCSR),语言模型以特定制约作为控制因素来填充推理模板。作为对模板CSR的处理方法,我们(一) 提出一套常识推理模板-扩展对的数据集,(二) 引入POTTTER,这是一个事先经过训练的序列到序列模型,使用速率来进行跨概念的共同推理。我们的实验表明,我们的方法在生成指标和事实质量指标方面都超过了基线。我们还就我们方法可靠地执行常识推理的能力提出了详细的错误分析。