We are inviting researchers interested in Natural Language Processing to participate in a shared task on Sarcasm and Sentiment Detection in Arabic associated with the 6th Workshop on Arabic Natural Language Processing at EACL 2021.
Website: https://sites.google.com/view/ar-sarcasm-sentiment-detection Registration: https://docs.google.com/forms/d/e/1FAIpQLSdHxKHLcyWMw3eATOzcVADyvyy6rMI2vt7sK08x34Ayg9xHJA/viewform
There are two subtasks in this shared task: Subtask 1 (Sarcasm Detection): Identifying whether a tweet is sarcastic or not, this is a binary classification task. Subtask 2 (Sentiment Analysis): Identifying the sentiment of a tweet and assigning one of three labels (Positive, Negative, Neutral), multiclass classification task.
*Important Dates for shared task:* Dec 6, 2020: First announcement of the shared task + registration open Jan 1, 2021: Release of the initial training data Jan 10, 2021: Registration Deadline Jan 21, 2021: Test Set made available Feb 1, 2021: Codalab System submission deadline Feb 10, 2021: Shared task system paper submissions due Feb 20, 2021: Notification of Acceptance Mar 1, 2021: Camera-ready version of shared task system papers due April 19-20, 2021: Workshop Dates
Metrics: Subtask 1: The evaluation metrics will include precision/recall/f-score/accuracy. F-score of the sarcastic class will be the official metric. Subtask 2: The evaluation metrics will include precision/recall/f-score/accuracy. F-PN (Macro average of the F-score of the positive and negative classes) will be the official metric.
Task Organizers Ibrahim Abu Farha (The University of Edinburgh), Wajdi Zaghouni (Hamad Bin Khalifa University) and Walid Magdy (The University of Edinburgh)
For questions or comments regarding WANLP-5 you may contact Wajdi Zaghouani: wzaghouani at hbku.edu.qa
The following resources might be helpful for participants: For the initial experimentation, participants can use the ArSarcasm dataset, which is publicly available below.
ArSarcasm dataset https://github.com/iabufarha/ArSarcasm
AraBERT https://github.com/aub-mind/arabert
Mazajak Word Embeddings http://mazajak.inf.ed.ac.uk:8000/#embedding-page
----
*Wajdi Zaghouani, Ph.D.*
*Assistant Professor* College of Humanities and Social Sciences
P.O. Box 34110 | Education City | Doha, Qatar tel: +974 4454 5601 | mob: +974 33454992
wzaghouani at hbku.edu.qa| Office A141, LAS Building -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 4719 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20201209/3a514cdc/attachment.txt>