We organised this shared task in the framework of the Evalita 2020 campaign. AcCompl-it aimed at developing and evaluating methods to classify Italian sentences according to Acceptability and Complexity.
The task has been conceived as a regression task articulated into the two following subtasks:
- ACCEPT subtask, which consists in providing an acceptability score on a 1-7 Likert scale for each sentence in the test set, along with an estimation of its standard error;
- COMPL subtask, which consists in providing a complexity score on a 1-7 Likert scale for each sentence in the test set, along with an estimate of its standard error.
For detailed documentation about the task, see the AcCompl-it website.
Download
Click here to download the dataset:
(Note: after filling in the request form, the download link will appear at the bottom of the page.)
References
Brunato D., Chesi C., Dell’Orletta F., Montemagni S., Venturi G., Zamparelli R. (2020). AcCompl-it@EVALITA2020: Overview of the Acceptability & Complexity Evaluation Task for Italian.”. In Proceedings of EVALITA ’20, Evaluation of NLP and Speech Tools for Italian, 16-17 December, Online, Italy.