no code implementations • nlppower (ACL) 2022 • Amr Keleg, Matthias Lindemann, Danyang Liu, Wanqiu Long, Bonnie L. Webber
Automatic evaluation indicates that removing straplines and noise from the training data of a news summarizer results in higher quality summaries, with improvements as high as 7 points ROUGE score.
1 code implementation • OSACT (LREC) 2022 • Amr Keleg, Walid Magdy
The Qur’an QA 2022 shared task aims at assessing the possibility of building systems that can extract answers to religious questions given relevant passages from the Holy Qur’an.
1 code implementation • 20 Oct 2023 • Amr Keleg, Walid Magdy
Automatic Arabic Dialect Identification (ADI) of text has gained great popularity since it was introduced in the early 2010s.
1 code implementation • 20 Oct 2023 • Amr Keleg, Sharon Goldwater, Walid Magdy
Transcribed speech and user-generated text in Arabic typically contain a mixture of Modern Standard Arabic (MSA), the standardized language taught in schools, and Dialectal Arabic (DA), used in daily communications.
1 code implementation • 8 Jun 2023 • Amr Keleg, Walid Magdy
A new benchmark DLAMA-v1 is built of factual triples from three pairs of contrasting cultures having a total of 78, 259 triples from 20 relation predicates.
no code implementations • LREC 2020 • Amr Keleg, Samhaa R. El-Beltagy, Mahmoud Khalil
In the past years, toxic comments and offensive speech are polluting the internet and manual inspection of these comments is becoming a tiresome task to manage.
2 code implementations • LREC 2020 • Amr Keleg, Francis Tyers, Nick Howell, Tommi Pirinen
In this paper, we have developed a method for weighting a morphological analyzer built using finite state transducers in order to disambiguate its results.