Ulrich Heid’s research while affiliated with University of Hildesheim and other places

We created a prototype of an electronic dictionary for the mathematical domain of graph theory. We evaluate our prototype and compare its effectiveness in task-­based tests with that of Wikipedia. Our dictionary is based on a corpus; the terms and their definitions were automatically extracted and annotated by experts (cf. Kruse/Heid 2020). The dictionary is bilingual, covering German and English; it gives equivalents, definitions and semantically related terms. For the implementation of the dictionary, we used LexO (Bellandi et al. 2017). The target group of the dictionary are students of mathematics who attend lectures in German and work with English resources. We carried out tests to understand which items the students search for when they work on graph-­theoretical tasks. We ran the same test twice, with comparable student groups, either allowing Wikipedia as an information source or our dictionary. The dictionary seems to be especially helpful for students who already have a vague idea of a term because they can use the resource to check if their idea is right.

Legal documents often have a complex layout with many different headings, headers and footers, side notes, etc. For the further processing, it is important to extract these individual components correctly from a legally binding document, for example a signed PDF. A common approach to do so is to classify each (text) region of a page using its geometric and textual features. This approach works well, when the training and test data have a similar structure and when the documents of a collection to be analyzed have a rather uniform layout. We show that the use of global page properties can improve the accuracy of text element classification: we first classify each page into one of three layout types. After that, we can train a classifier for each of the three page types and thereby improve the accuracy on a manually annotated collection of 70 legal documents consisting of 20,938 text elements. When we split by page type, we achieve an improvement from 0.95 to 0.98 for single-column pages with left marginalia and from 0.95 to 0.96 for double-column pages. We developed our own feature-based method for page layout detection, which we benchmark against a standard implementation of a CNN image classifier. The approach presented here is based on corpus of freely available German contracts and general terms and conditions. Both the corpus and all manual annotations are made freely available. The method is language agnostic.

1. Introduction Michael Rundell Sue Atkins, who died in September at the age of 90, was a true visionary, and one of the most important and influential lexicographers of this or any other era. Her long and distinguished career began in the 1960s — when dictionary-making inhabited a rather amateurish, index-carded (and male-dominated) milieu — and continued well into the 21st century. By the time Sue retired (if she ever truly did), corpus-based lexicography was the norm, collaborations between lexicographers and linguists were almost routine, and tools for semi-automatic dictionary compilation were already well advanced. But the important point here is not simply that Sue lived through these dramatic changes — she was one of the key people driving them, and her impact will continue to be felt for years to come. The eight pieces collected here come from friends and colleagues who worked with Sue at different points in her career. They testify to her massive contributions across the range of activities — technical, theoretical, and practical — which her career spanned. They also show the great admiration and affection in which Sue was held by all who knew her and worked with her. Reading these reminiscences, one can’t help noticing a number of recurrent themes: her remarkable insight into the nature of language; her readiness to engage with people from other communities (academic linguists, computer scientists, and so on) in order to take things forward; her boundless energy and infectious enthusiasm; her organisational skills and talent for getting things done (and for knowing what needed to be done); and her wit, charm, and great capacity for fun and friendship. Whatever the situation, Sue was always good company, as many of these reminiscences attest.

Online-Rezensionen zu künstlerischen Artefakten können Bildungsprozesse anstoßen. Sowohl in der produktiven Auseinandersetzung mit einem Werk als auch in der Aufbereitung dieser Erfahrung in einem rezensiven Text und für ein spezifisches Publikum liegt ein hohes Potenzial hinsichtlich der kulturellen Teilhabe und Überwindung von Bildungsbarrieren. Aber welche Prozesse, Inhalte und Kontexte spielen dabei eine Rolle? Dieser Frage widmete sich das interdisziplinäre Forschungsprojekt Rez@Kultur, dessen Ergebnisse hier erstmals umfassend dargestellt werden. Ergänzt werden die Befunde um Anschlussperspektiven und Kommentare aus Forschung und Praxis.

Online-Rezensionen zu künstlerischen Artefakten können Bildungsprozesse anstoßen. Sowohl in der produktiven Auseinandersetzung mit einem Werk als auch in der Aufbereitung dieser Erfahrung in einem rezensiven Text und für ein spezifisches Publikum liegt ein hohes Potenzial hinsichtlich der kulturellen Teilhabe und Überwindung von Bildungsbarrieren. Aber welche Prozesse, Inhalte und Kontexte spielen dabei eine Rolle? Dieser Frage widmete sich das interdisziplinäre Forschungsprojekt Rez@Kultur, dessen Ergebnisse hier erstmals umfassend dargestellt werden. Ergänzt werden die Befunde um Anschlussperspektiven und Kommentare aus Forschung und Praxis.