This study addresses the issue of the change in the concept of security threats due to developments in the field of technology, as the issue of cyber security has become one of the major challenges faced by countries at the regional and global levels
, especially with the increasing volume of cyber threats that affect the information security of countries.
Today, cyber security is one of the most important concepts that countries seek to achieve, especially after technological progress and the extent of the impact of this progress on the national security of countries, which necessitated the development of defensive security strategies to repel cyber-attacks and work to develop the cyber capabilities of countries.
This study will focus on the most important concepts in cyberspace and the main actors in the practice of cyber-attacks, in addition to identifying the Iranian security strategy in the cyber field.
The study reached results and recommendations, the most important of which is that cyberspace has become a new arena for international conflict and the need to develop defensive strategies to repel and detect cyber attacks.
Language representations are known to carry stereotypical biases and, as a result, lead to biased predictions in downstream tasks. While existing methods are effective at mitigating biases by linear projection, such methods are too aggressive: they n
ot only remove bias, but also erase valuable information from word embeddings. We develop new measures for evaluating specific information retention that demonstrate the tradeoff between bias removal and information retention. To address this challenge, we propose OSCaR (Orthogonal Subspace Correction and Rectification), a bias-mitigating method that focuses on disentangling biased associations between concepts instead of removing concepts wholesale. Our experiments on gender biases show that OSCaR is a well-balanced approach that ensures that semantic information is retained in the embeddings and bias is also effectively mitigated.
Byte-pair encoding (BPE) is a ubiquitous algorithm in the subword tokenization process of language models as it provides multiple benefits. However, this process is solely based on pre-training data statistics, making it hard for the tokenizer to han
dle infrequent spellings. On the other hand, though robust to misspellings, pure character-level models often lead to unreasonably long sequences and make it harder for the model to learn meaningful words. To alleviate these challenges, we propose a character-based subword module (char2subword) that learns the subword embedding table in pre-trained models like BERT. Our char2subword module builds representations from characters out of the subword vocabulary, and it can be used as a drop-in replacement of the subword embedding table. The module is robust to character-level alterations such as misspellings, word inflection, casing, and punctuation. We integrate it further with BERT through pre-training while keeping BERT transformer parameters fixed--and thus, providing a practical method. Finally, we show that incorporating our module to mBERT significantly improves the performance on the social media linguistic code-switching evaluation (LinCE) benchmark.
It is widely accepted that fine-tuning pre-trained language models usually brings about performance improvements in downstream tasks. However, there are limited studies on the reasons behind this effectiveness, particularly from the viewpoint of stru
ctural changes in the embedding space. Trying to fill this gap, in this paper, we analyze the extent to which the isotropy of the embedding space changes after fine-tuning. We demonstrate that, even though isotropy is a desirable geometrical property, fine-tuning does not necessarily result in isotropy enhancements. Moreover, local structures in pre-trained contextual word representations (CWRs), such as those encoding token types or frequency, undergo a massive change during fine-tuning. Our experiments show dramatic growth in the number of elongated directions in the embedding space, which, in contrast to pre-trained CWRs, carry the essential linguistic knowledge in the fine-tuned embedding space, making existing isotropy enhancement methods ineffective.
How do people understand the meaning of the word small'' when used to describe a mosquito, a church, or a planet? While humans have a remarkable ability to form meanings by combining existing concepts, modeling this process is challenging. This paper
addresses that challenge through CEREBRA (Context-dEpendent meaning REpresentations in the BRAin) neural network model. CEREBRA characterizes how word meanings dynamically adapt in the context of a sentence by decomposing sentence fMRI into words and words into embodied brain-based semantic features. It demonstrates that words in different contexts have different representations and the word meaning changes in a way that is meaningful to human subjects. CEREBRA's context-based representations can potentially be used to make NLP applications more human-like.
Natural language often exhibits inherent hierarchical structure ingrained with complex syntax and semantics. However, most state-of-the-art deep generative models learn embeddings only in Euclidean vector space, without accounting for this structural
property of language. In this paper, we investigate text generation in a hyperbolic latent space to learn continuous hierarchical representations. An Adversarial Poincare Variational Autoencoder (APo-VAE) is presented, where both the prior and variational posterior of latent variables are defined over a Poincare ball via wrapped normal distributions. By adopting the primal-dual formulation of Kullback-Leibler divergence, an adversarial learning procedure is introduced to empower robust model training. Extensive experiments in language modeling, unaligned style transfer, and dialog-response generation demonstrate the effectiveness of the proposed APo-VAE model over VAEs in Euclidean latent space, thanks to its superb capabilities in capturing latent language hierarchies in hyperbolic space.
Abstract Most combinations of NLP tasks and language varieties lack in-domain examples for supervised training because of the paucity of annotated data. How can neural models make sample-efficient generalizations from task--language combinations with
available data to low-resource ones? In this work, we propose a Bayesian generative model for the space of neural parameters. We assume that this space can be factorized into latent variables for each language and each task. We infer the posteriors over such latent variables based on data from seen task--language combinations through variational inference. This enables zero-shot classification on unseen combinations at prediction time. For instance, given training data for named entity recognition (NER) in Vietnamese and for part-of-speech (POS) tagging in Wolof, our model can perform accurate predictions for NER in Wolof. In particular, we experiment with a typologically diverse sample of 33 languages from 4 continents and 11 families, and show that our model yields comparable or better results than state-of-the-art, zero-shot cross-lingual transfer methods. Our code is available at github.com/cambridgeltl/parameter-factorization.
With increased attention to regional and spatial planning in the world and the need to pay
attention to modern spatial development methods, increased thinking for necessity urban
networks as a mechanism for achieving spatial development in small an
d medium-sized
cities, operating alone, has been enhanced by changing the spatial structure of the
Territory, raising qualitative and quantitative use, To collect the assets and resources of the
cities of the Region that accept participation in potential opportunities and risks.
The analytical study was implemented by proposing an urban network in the Greater
Damascus Region that examines the nodes and links, and uses the SWOT system to
examine opportunities and possibilities, its relationship to the problems and determinants
of selecting the best scenario for the proposed urban network examines the effect of
applying the urban network concept on changing the spatial structure of the Greater
Damascus Region, and propose a workable mechanism at the spatial-sectorial level.
The research concludes with a set of conclusions and recommendations that determine the
importance of the networking of cities according to their location, which is capable of
adapting to the changes taking place in our Syrian cities. In the absence of a future vision
for regional development that is appropriate to the current situation, taking into account the
economic, social and spatial changes taking place; and which hinder the achievement of
the proposed national framework for regional planning in 2010.
choose the right way to dividing set of data with high dimensions to clusters in specific field and comparison the different subspace clustering algorithms and present the applications and usage
يشمل الفضاء الطباعي "النَّصي" طريقة تصميم الغلاف, و وضع المطالع و الخواتيم, و تنظيم الفصول, و تشكيل العنوانات... و غيرها. و هو يفتح أفقاً تأويلياً للبحوث الأدبية, كهذا البحث الذي يحاول إظهار أهميَّة الأثر الكتابي من نوع الخط, و الألوان, و النسق التتا
بعي, و البياض, و السواد, و تصميم الصفحة, في إذكاء خيال المتلقي.
و يؤكد البحث أن عملية اختيار العنوان هي أعقل مرحلة يمر بها صاحب النَّص, و لقد احتلَّ مكانة خاصة في ساحات الإبداع الأدبي, مما جعل الحاجة ملحَّة لوضع علم خاص به, و مستقل, هو "علم العنونة".
و يأتي هذا البحث بوصفه محاولة في قراءة كتاب "سيَّاف الزهور" لمحمد الماغوط باستخدام كل تلك الأدوات الإجرائية, مع محاولة التقيد بحدود ما تسمح به اللياقة الأدبيَّة, و المعرفة السليمة المبنيَّة على ما يقوله النَّص, فلا يجبره على ما ليس فيه.
