Referring to the recently seen: reference and perceptual memory in situated dialog
John D. Kelleher ADAPT Research Centre ICE Research Institute Technological University Dublin Simon Dobnik CLASP and FLOV University of Gotenburg, Sweden
Abstract
From theoretical linguistic and cognitive perspectives, situated dialog systems are interesting as they provide ideal test-beds for investigating the interaction between language and perception. At the same time there are a growing number of practical applications, for example robotic systems and driver-less cars, where spoken interfaces, capable of situated dialog, promise many advantages. To date, however much of the work on situated dialog has focused resolving anaphoric or exophoric references. This paper, by contrast, opens up the question of how perceptual memory and linguistic references interact, and the challenges that this poses to computational models of perceptually grounded dialog.
中文速览
机器人、无人驾驶汽车等场景中，人与系统对话时常常会提到"刚才看到但现在已经不在视野里"的东西，而现有的对话系统几乎都只能处理当前还能被感知到的指称对象，一旦目标消失就束手无策。这篇论文正面提出了这一被长期忽视的问题——如何让计算机系统具备"感知记忆（perceptual memory）"，从而解析对已消失实体的指称。作者综合认知心理学的记忆理论（工作记忆、情节缓冲区等）和语言学的指称理论，梳理了构建感知记忆数据结构面临的核心挑战，并对比了两种主要思路：局部/情节式架构（为每次感知事件保存独立片段）和整体式演化地图架构（将所有感知融合进一张持续更新的地图）。论文最终指出，这两种方案各有所长但均不完整，真正能支撑情境对话的系统需要将二者结合，这对人机交互和认知科学研究都具有重要的启示意义。
原文 arXiv:1903.09866;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1903.09866v1