We investigate the potential of using ChatGPT to annotate complex linguistic phenomena, such as language of evaluation, attitude and emotion. For this, we automatically annotate 11 texts in English, which represent spoken popular science, and evaluate the annotations manually. Our results show that ChatGPT has good precision in itemisation, i.e. detecting linguistic items in the text that carry evaluative meaning. However, we also find that the recall is very low. Besides that, we state that the tool fails in labeling the detected items with the correct categories on a more fine-grained level of granularity. We analyse the errors to find systematic errors related to specific categories in the annotation scheme.

In this paper, we describe results of a study on evaluation of intralingual machine translation. The study focuses on machine translations of medical texts into Plain German. The automatically simplified texts were compared with manually simplified texts (i.e., simplified by human experts) as well as with the underlying, unsimplified source texts. We analyse the quality of the translations based on different criteria, such as correctness, readability, and syntactic complexity. The study revealed that the machine translations were easier to read than the source texts, but contained a higher number of complex syntactic relations than the human translations. Furthermore, we identified various types of mistakes. These included not only grammatical mistakes but also content-related mistakes that resulted, for example, from mistranslations of grammatical structures, ambiguous words or numbers, omissions of relevant prefixes or negation, and incorrect explanations of technical terms.

In this paper, we describe results of a study on evaluation of intralingual machine translation. The study focuses on machine translations of medical texts into Plain German. The automatically simplified texts were compared with manually simplified texts (i.e., simplified by human experts) as well as with the underlying, unsimplified source texts. We analyse the quality of outputs from three models based on different criteria, such as correctness, readability, and syntactic complexity. We compare the outputs of the three models under analysis between each other, as well as with the existing human translations. The study revealed that system performance depends on the evaluation criteria used and that only one of the three models showed strong similarities to the human translations. Furthermore, we identified various types of errors in all three models. These included not only grammatical mistakes and misspellings, but also incorrect explanations of technical terms and false statements, which in turn led to serious content-related mistakes.

This study sets out to investigate the feasibility of using ChatGPT to translate citizen-oriented administrative texts into German Easy Language, a simplified, rule-based language variety that is adapted to the needs of people with reading impairments. We use ChatGPT to translate selected texts from websites of German public authorities using two strategies, i.e. linguistic and holistic. We analyse the quality of the generated texts based on different criteria, such as correctness, readability, and syntactic complexity. The results indicated that the generated texts are easier than the standard texts, but that they still do not fully meet the established Easy Language standards. Additionally, the content is not always rendered correctly.