We investigate a specific subtype of implicitly abusive language, focusing on non-negative sentences about identity groups (e.g.Women make good cooks).We introduce a novel dataset comprising such utterances.It not only profiles abusive sentences but also includes various semantic variants of the same characteristic attributed to an identity group, allowing us to systematically examine the impact of different degrees of generalization and perspective framing.Thus we demonstrate that specific variants significantly intensify the perception of abusiveness.By switching identity groups, we highlight how the characteristics often described in stereotypes are not inherently abusive.We also report on classification experiments.

We address the task of identifying euphemistic abuse (e.g.You inspire me to fall asleep) paraphrasing simple explicitly abusive utterances (e.g.You are boring).For this task, we introduce a novel dataset that has been created via crowdsourcing.Special attention has been paid to the generation of appropriate negative (nonabusive) data.We report on classification experiments showing that classifiers trained on previous datasets are less capable of detecting such abuse.Best automatic results are obtained by a classifier that augments training data from our new dataset with automatically-generated GPT-3 completions.We also present a classifier that combines a few manually extracted features that exemplify the major linguistic phenomena constituting euphemistic abuse.

We demonstrate a toolchain for visualising detailed road traffic data from multimodal sensors consisting of (i) the automatic, real-time extraction of movement paths of road users and noteworthy events from traffic monitoring cameras or LIDAR sensors, (ii) extraction of audio events from individual microphones and microphone arrays, (iii) a spatial data managment system storing the extracted information together with a geographic information system (GIS), and (iv) a web based viewer allowing to interactively visualise all these data in the context of a high-definition digital twin of the traffic environment. This system enables the collection of a considerable amount of objective data on road use and can be used for planning changes to traffic facilities as well as for assessing changes in the traffic environment.

The exploding amount of user-generated content has spurred NLP research to deal with documents from various digital communication formats (tweets, chats, emails, etc.). Using these texts as language resources implies complying with legal data privacy regulations. To protect the personal data of individuals and preclude their identification, we employ pseudonymization. More precisely, we identify those text spans that carry information revealing an individual’s identity (e.g., names of persons, locations, phone numbers, or dates) and subsequently substitute them with synthetically generated surrogates. Based on CodE Alltag, a German-language email corpus, we address two tasks. The first task is to evaluate various architectures for the automatic recognition of privacy-sensitive entities in raw data. The second task examines the applicability of pseudonymized data as training data for such systems since models learned on original data cannot be published for reasons of privacy protection. As outputs of both tasks, we, first, generate a new pseudonymized version of CodE Alltag compliant with the legal requirements of the General Data Protection Regulation (GDPR). Second, we make accessible a tagger for recognizing privacy-sensitive information in German emails and similar text genres, which is trained on already pseudonymized data.

Michael Wiegand, Elisabeth Eder, Josef Ruppenhofer. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

To track different levels of formality in written discourse, we introduce a novel type of lexicon for the German language, with entries ordered by their degree of (in)formality.We start with a set of words extracted from traditional lexicographic resources, extend it by sentence-based similarity computations, and let crowdworkers assess the enlarged set of lexical items on a continuous informal-formal scale as a gold standard for evaluation.We submit this lexicon to an intrinsic evaluation related to the best regression models and their effect on predicting formality scores and complement our investigation by an extrinsic evaluation of formality on a German-language email corpus.

Michael Wiegand, Josef Ruppenhofer, Elisabeth Eder. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

The vast amount of social communication distributed over various electronic media channels (tweets, blogs, emails, etc.), so-called user-generated content (UGC), creates entirely new opportunities for today’s NLP research. Yet, data privacy concerns implied by the unauthorized use of these text streams as a data resource are often neglected. In an attempt to reconciliate the diverging needs of unconstrained raw data use and preservation of data privacy in digital communication, we here investigate the automatic recognition of privacy-sensitive stretches of text in UGC and provide an algorithmic solution for the protection of personal data via pseudonymization. Our focus is directed at the de-identification of emails where personally identifying information does not only refer to the sender but also to those people, locations, dates, and other identifiers mentioned in greetings, boilerplates and the content-carrying body of emails. We evaluate several de-identification procedures and systems on two hitherto non-anonymized German-language email corpora (CodE AlltagS+d and CodE AlltagXL), and generate fully pseudonymized versions for both (CodE Alltag 2.0) in which personally identifying information of all social actors addressed in these mails has been camouflaged (to the greatest extent possible).