The detection of reused text is important in a wide range of disciplines. However, even as research in the field of plagiarism detection is constantly improving, heavily modified or paraphrased text is still challenging for current methodologies. For historical texts, these problems are even more severe, since text sources were often subject to stronger and more frequent modifications. Despite the need for tools to automate text criticism, e.g., tracing modifications in historical text, algorithmic support is still limited. While current techniques can tell if and how frequently a text has been modified, very little work has been done on determining the degree and kind of paraphrastic modification—despite such information being of substantial interest to scholars. We present a human-interpretable, feature-based method to measure paraphrastic modification. Evaluating our technique on three data sets, we find that our approach performs competitive to text similarity scores borrowed from machine translation evaluation, being much harder to interpret.

The Open Philology Project at the University of Leipzig aspires to re-assert the value of philology in its broadest sense. Philology signifies the widest possible use of the linguistic record to enable a deep understanding of the complete lived experience of humanity. Pragmatically, we focus on Greek and Latin because (1) substantial collections and services are already available within these languages, (2) substantial user communities exist (c. 35,000 unique users a month at the Perseus Digital Library), and (3) a European-based project is better positioned to process extensive cultural heritage materials in these languages rather than in Chinese or Sanskrit. The Open Philology Project has been designed with the hope that it can contribute to any historical language that survives within the human record. It includes three tasks: (1) the creation of an open, extensible, repurposable collection of machine-readable linguistic sources; (2) the development of dynamic textbooks that use annotated corpora to customize the vocabulary and grammar of texts that learners want to read, and at the same time engage students in collaboratively producing new annotated data; (3) the establishment of new workflows for, and forms of, publication, from individual annotations with argumentation to traditional publications with integrated machine-actionable data.