可控常识推理的模板填充
Template Filling for Controllable Commonsense Reasoning
摘要：
大规模的序列到序列模型已经被证明是擅长于多项选择和开放领域的常识推理任务。然而，当前的系统不提供控制推理链的各种属性的能力。为了使更好的可控性，我们建议研究的常识推理作为一个模板填充任务（TemplateCSR）-其中的语言模型填充推理模板与给定的约束作为控制因素。作为TemplateCSR的一种方法，我们（i）提出了一个常识推理模板扩展对的数据集，（ii）引入了POTTER，一个预先训练的序列到序列模型，使用提示在概念之间执行常识推理。我们的实验表明，我们的方法优于基线生成度量和真实性度量。我们还提出了一个详细的错误分析，我们的方法的能力，可靠地执行常识推理。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
