Personal nouns, i.e. common nouns denoting human beings, play an important role in manifesting gender and gender stereotypes in texts, especially for languages with grammatical gender like German. Automatically detecting and extracting personal nouns can thus be of interest to a myriad of different tasks such as minimizing gender bias in language models and researching gender stereotypes or gender-fair language, but is complicated by the morphological heterogeneity and homonymy of personal and non-personal nouns, which restrict lexicon-based approaches. In this paper, we introduce a classifier created by fine-tuning a transformer model that detects personal nouns in German. Although some phenomena like homonymy and metalinguistic uses are still problematic, the model is able to classify personal nouns with robust accuracy (f1-score: 0.94).

Most annotation efforts assume that annotators will agree on labels, if the annotation categories are well-defined and documented in annotation guidelines. However, this is not always true. For instance, content-related questions such as ‘Is this sentence about topic X?’ are unlikely to elicit the same answer from all annotators. Additional specifications in the guidelines are helpful to some extent, but can soon get overspecified by rules that cannot be justified by a research question. In this study, we model the semantic category ‘illness’ and its use in a gradual way. For this purpose, we (i) ask many annotators (30 votes per item, 960 items) for their opinion in a crowdsourcing experiment, (ii) ask annotators to indicate their certainty with respect to their annotation, and (iii) compare this across two different text types. We show that results of multiple annotations and average annotator certainty correlate, but many ambiguities can only be captured if several people contribute. The annotated data allow us to filter for sentences with high or low agreement and analyze causes of disagreement, thus getting a better understanding of people’s perception of illness—as an example of a semantic category—as well as of the content of our annotated texts.

The concept of style is much debated in theoretical as well as empirical terms. From an empirical perspective, the key question is how to operationalize style and thus make it accessible for annotation and quantification. In authorship attribution, many different approaches have successfully resolved this issue at the cost of linguistic interpretability: The resulting algorithms may be able to distinguish one language variety from the other, but do not give us much information on their distinctive linguistic properties. We approach the issue of interpreting stylistic features by extracting linear and syntactic n-grams that are distinctive for a language variety. We present a study that exemplifies this process by a comparison of the German academic languages of linguistics and literary studies. Overall, our findings show that distinctive n-grams can be related to linguistic categories. The results suggest that the style of German literary studies is characterized by nominal structures and the style of linguistics by verbal ones.