Putting collation of text witnesses on a formal basis

This article presents an approach to the collation problem of text witnesses which is correct for all distance functions and is applicable to the alignment of any types of tokens, be it letters, words, sentences, or paragraphs. In contrast to the existing approaches, which all are heuristics in nature, we specify a formal model in the form of an integer linear program (ILP) that formally describes the optimization problem. For a special case that usually occurs in practice, we then transfer the ILP into an efficient algorithm that optimally solves the alignment problem. In the second part of the article, we apply our approach to the alignment of paragraphs of text witnesses—an alignment problem that has received little attention in the literature so far—and compare the results of our approach, which we have called TSaligner, with those of CollateX.