比较词、量词、比例词:一个从视觉中学习量词的多任务模型
Comparatives, Quantifiers, Proportions: A Multi-Task Model for the Learning of Quantities from Vision
摘要:
目前的工作调查是否不同的量化机制(集比较,模糊量化,比例估计)可以联合学习从视觉场景的多任务计算模型。动机是,在人类中,这些过程是相同的认知,非符号能力的基础,这使得自动估计和比较设定的幅度。我们表明,当低复杂度的任务的信息是可用的,更高级别的比例任务变得更准确,比孤立执行时。此外,多任务模型能够推广到目标/非目标对象的看不见的组合。与比例任务中绝对数量干扰的行为证据一致,当被要求提供场景中目标物体的数量时,多任务模型不再起作用。
英文摘要:
The present work investigates whether different quantification mechanisms (set comparison, vague quantification, and proportional estimation) can be jointly learned from visual scenes by a multi-task computational model. The motivation is that, in humans, these processes underlie the same cognitive, non-symbolic ability, which allows an automatic estimation and comparison of set magnitudes. We show that when information about lower-complexity tasks is available, the higher-level proportional task becomes more accurate than when performed in isolation. Moreover, the multi-task model is able to generalize to unseen combinations of target/non-target objects. Consistently with behavioral evidence showing the interference of absolute number in the proportional task, the multi-task model no longer works when asked to provide the number of target objects in the scene.
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。