In this paper we study the approximate minimization problem for language modelling. We assume we are given some language model as a black box. The objective is to obtain a weighted finite automaton (WFA) that fits within a given size constraint and which mimics the behaviour of the original model while minimizing some notion of distance between the black box and the extracted WFA. We provide an algorithm for the approximate minimization of black boxes trained for language modelling of sequential data over a one-letter alphabet. By reformulating the problem in terms of Hankel matrices, we leverage classical results on the approximation of Hankel operators, namely the celebrated Adamyan-Arov-Krein (AAK) theory. This allows us to use the spectral norm to measure the distance between the black box and the WFA. We provide theoretical guarantees to study the potentially infinite-rank Hankel matrix of the black box, without accessing the training data, and we prove that our method returns an asymptotically-optimal approximation.
翻译:在本文中,我们研究了语言建模的最小化问题。 我们假设我们得到了一些语言模型,作为黑盒。 目标是获得一个符合一定尺寸限制的加权限量自动图(WFA),它模仿原始模型的行为,同时将黑盒与提取的WFA之间的距离概念最小化。 我们为在单字母字母字母字母基础上进行顺序数据模拟培训的黑盒的大致最小化提供了算法。 通过重塑汉克尔矩阵的问题,我们利用汉克尔操作员近似(即著名的阿达米安-阿罗夫-克林(AAK)理论)的经典结果。 这使我们能够使用光谱规范来衡量黑盒与WFA之间的距离。 我们提供理论保证,研究黑盒中潜在的无限汉克尔矩阵,而没有获得培训数据,我们证明我们的方法返回了一种无症状的最佳近似的近似值。