采取行动以实现流畅交互:执行动作对指令澄清请求策略建模的影响
Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests
AI总结:
本研究探究动作执行作为辅助任务对指令澄清请求策略建模的影响,发现其贡献有限,Transformer模型难掌握发起时机但可较好确定询问内容,并讨论了数据驱动范式学习元沟通行为的缺陷。
摘要:
澄清请求是指令遵循交互中用于解决因歧义或描述不足等导致的沟通问题的机制。尽管其重要性不言而喻,即便性能出色的模型也难以生成或解读这类修复行为。本研究中,我们验证了三项关于将动作执行作为辅助任务对iCR(指令澄清请求)策略建模影响的假设。与最初预期相反,我们发现其对学习iCR策略的贡献有限,但仍可从预测不确定性中提取部分信息。我们进一步提供证据表明,即便设计合理的基于Transformer的模型也无法学习到何时发起指令澄清请求的优质策略,不过确定该询问什么内容的任务建模效果更佳。结合这些发现的启示,我们还讨论了数据驱动范式在学习元沟通行为方面的不足。
英文摘要:
Clarification requests are a mechanism to help solve communication problems, e.g. due to ambiguity or underspecification, in instruction-following interactions. Despite their importance, even skilful models struggle with producing or interpreting such repair acts. In this work, we test three hypotheses concerning the effects of action taking as an auxiliary task in modelling iCR policies. Contrary to initial expectations, we conclude that its contribution to learning an iCR policy is limited, but some information can still be extracted from prediction uncertainty. We present further evidence that even well-motivated, Transformer-based models fail to learn good policies for when to ask Instruction CRs (iCRs), while the task of determining what to ask about can be more successfully modelled. Considering the implications of these findings, we further discuss the shortcomings of the data-driven paradigm for learning meta-communication acts.
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。