论文标题
使用复杂性测量类比转移的可行性
Measuring the Feasibility of Analogical Transfer using Complexity
论文作者
论文摘要
类比是形式的4-元素关系“ a a to b to b as c ins d d d d”。虽然焦点主要是在如何解决类比的方式上，即如何找到给定的A，B和C的正确值，但对解决这种类比是否实际上是可行的较少关注。在本文中，我们建议对源案例（a和b）的可转移性解决目标问题C进行定量。此量化基于一个复杂性最小化原理，该原理已被证明可以有效地解决类比。我们说明了这些关于形态类似物的概念，并显示了它与机器学习的联系，尤其是无监督的域适应性。
Analogies are 4-ary relations of the form "A is to B as C is to D". While focus has been mostly on how to solve an analogy, i.e. how to find correct values of D given A, B and C, less attention has been drawn on whether solving such an analogy was actually feasible. In this paper, we propose a quantification of the transferability of a source case (A and B) to solve a target problem C. This quantification is based on a complexity minimization principle which has been demonstrated to be efficient for solving analogies. We illustrate these notions on morphological analogies and show its connections with machine learning, and in particular with Unsupervised Domain Adaptation.
