The objective of this work was the introduction of an effective approach based on the AraBERT language model for fighting Tweets COVID-19 Infodemic. It was arranged in the form of a two-step pipeline, where the first step involved a series of pre-pro
cessing procedures to transform Twitter jargon, including emojis and emoticons, into plain text, and the second step exploited a version of AraBERT, which was pre-trained on plain text, to fine-tune and classify the tweets with respect to their Label. The use of language models pre-trained on plain texts rather than on tweets was motivated by the necessity to address two critical issues shown by the scientific literature, namely (1) pre-trained language models are widely available in many languages, avoiding the time-consuming and resource-intensive model training directly on tweets from scratch, allowing to focus only on their fine-tuning; (2) available plain text corpora are larger than tweet-only ones, allowing for better performance.
Subtle and overt racism is still present both in physical and online communities today and has impacted many lives in different segments of the society. In this short piece of work, we present how we're tackling this societal issue with Natural Langu
age Processing. We are releasing BiasCorp, a dataset containing 139,090 comments and news segment from three specific sources - Fox News, BreitbartNews and YouTube. The first batch (45,000 manually annotated) is ready for publication. We are currently in the final phase of manually labeling the remaining dataset using Amazon Mechanical Turk. BERT has been used widely in several downstream tasks. In this work, we present hBERT, where we modify certain layers of the pretrained BERT model with the new Hopfield Layer. hBert generalizes well across different distributions with the added advantage of a reduced model complexity. We are also releasing a JavaScript library 3 and a Chrome Extension Application, to help developers make use of our trained model in web applications (say chat application) and for users to identify and report racially biased contents on the web respectively
Children are the most damaged group affected by crimes of terrorism, suffering numerous forms of aggression. Due to the terrorism which has violently disrupted Syria previously, the phenomenon of recruiting children into combat and related actions mo
tivated the law to release the Legal Decree n. /11/ for the year 2013 which criminalizes the recruitment and employment of children in combat.
The publication of this law has developed a new contradictory situation where it has made the recruited child both a victim and a criminal at the same time.
Therefore, the child is considered a victim in the recruitment and deployment of combat which aims to polytheism them in the fighting actions, while at the same time the child is also considered as being responsible for the crimes that he
ventured to do during his recruitment period. This presents an unacceptable contrast within the law.
The subject of this study is to identify the children which have been recruited by the armed terrorist groups, and to show the features displayed which distinguish such children from other children who are involved in criminal activity with the
aim of defining the legal position for these recruited children and their responsibility towards the crimes that they have committed during their recruitment period.
