@inproceedings{schneider2023hard, type = {inproceedings}, key = {schneider2023hard}, title = {Hard is the Task, the Samples are Few: A German Chiasmus Dataset}, author = {Felix Schneider and Sven Sickert and Phillip Brandes and Sophie Marshall and Joachim Denzler}, booktitle = {Language Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics (LTC)}, year = {2023}, address = {Poznan, Poland}, pages = {255-260}, code = {https://github.com/cvjena/chiasmus-annotations}, doi = {10.14746/amup.9788323241775}, abstract = {In this work we present a novel German language dataset for the detection of the stylistic device called chiasmus collected from German dramas. The dataset includes phrases labeled as chiasmi, antimetaboles, semantically unrelated inversions, and various edge cases. The dataset was created by collecting examples from the GerDraCor dataset. We test different approaches for chiasmus detection on the samples and report an average precision of 0.74 for the best method. Additionally, we give an overview about related approaches and the current state of the research on chiasmus detection.}, note = {}, }