Structural Alignment as the Basis to Improve Significant Change Detection in Versioned Sentences

Some revisions of documents can change the meaning of passages, while others merely re-phrase or improve style. In a multi-author workflow, assisting readers to assess whether a revision changes meaning or not can be useful in prioritising revision. One challenge in this is how to detect and represent the revision changes in a meaningful way to assist users in assessing the impact of revision changes. This paper explores a segmentation approach which utilises the syntactic context of revisions to support assessment of significant changes. We observe that length of normalised edit distance or Word Error Rate (WER) correlates better to the significance of the revision changes at sentence level compared to general sentence similarity approaches. We show that our proposed method, SAVeS, supports improved analysis of change significance through alignment of segments rather than words. SAVeS can be used as the basis for a computational approach to identify significant revision changes.