The Gender Cross-Genre (GxG) task is a shared task on author profiling (in terms of gender) on Italian texts, with a specific focus on cross-genre performance. This task has been proposed for the first time at EVALITA 2018, providing different datasets from different textual genres: Twitter, YouTube, Children writing, Journalism, Personal diaries. Results from a total of 50 different runs show that the task is difficult to learn in itself: while almost all runs beat a 50% baseline, no model reaches an accuracy above 70%. We also observe that cross-genre modelling yields a drop in performance, but not as substantial as one would expect.
Overview of the Evalita 2018 cross-genre gender prediction (GXG) task
Dell'Orletta F;
2018
Abstract
The Gender Cross-Genre (GxG) task is a shared task on author profiling (in terms of gender) on Italian texts, with a specific focus on cross-genre performance. This task has been proposed for the first time at EVALITA 2018, providing different datasets from different textual genres: Twitter, YouTube, Children writing, Journalism, Personal diaries. Results from a total of 50 different runs show that the task is difficult to learn in itself: while almost all runs beat a 50% baseline, no model reaches an accuracy above 70%. We also observe that cross-genre modelling yields a drop in performance, but not as substantial as one would expect.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
