Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Deep Metric Learning Approach to Account Linking
نهج التعلم المتري العميق لحساب الربط
313
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نحن نعتبر مهمة ربط حسابات وسائل الاعلام الاجتماعية التي تنتمي إلى المؤلف نفسه في أزياء آلية على أساس المحتوى والبيانات التعريف لتدفقات المستندات المقابلة.نركز على تعلم التضمين الذي يقوم بخرائط عينات ذات حجم متغير من نشاط المستخدم - بدءا من مشاركات واحدة بأكمله أشهر من النشاط - إلى مساحة متجهية، حيث عينات من نفس خريطة المؤلف إلى النقاط القريبة.لا يتطلب نهجنا بيانات مشروح من البشر لأغراض تدريبية، مما يتيح لنا الاستفادة من كميات كبيرة من محتوى وسائل التواصل الاجتماعي.تتفوق النموذج المقترح على العديد من خطوط الأساس التنافسية بموجب إطار تقييم رواية على غرار بعد معايير الاعتراف المنشأة في مجالات أخرى.إن طريقتنا تحقق دقة ربط عالية، حتى مع عينات صغيرة من الحسابات غير المرجة في وقت التدريب، شرط أساسي للتطبيقات العملية لإطار الارتباط المقترح.
We consider the task of linking social media accounts that belong to the same author in an automated fashion on the basis of the content and meta-data of the corresponding document streams. We focus on learning an embedding that maps variable-sized samples of user activity--ranging from single posts to entire months of activity--to a vector space, where samples by the same author map to nearby points. Our approach does not require human-annotated data for training purposes, which allows us to leverage large amounts of social media content. The proposed model outperforms several competitive baselines under a novel evaluation framework modeled after established recognition benchmarks in other domains. Our method achieves high linking accuracy, even with small samples from accounts not seen at training time, a prerequisite for practical applications of the proposed linking framework.
References used
https://aclanthology.org/
rate research
Read More
There is an emerging interest in the application of natural language processing models to source code processing tasks. One of the major problems in applying deep learning to software engineering is that source code often contains a lot of rare ident
ifiers, resulting in huge vocabularies. We propose a simple, yet effective method, based on identifier anonymization, to handle out-of-vocabulary (OOV) identifiers. Our method can be treated as a preprocessing step and, therefore, allows for easy implementation. We show that the proposed OOV anonymization method significantly improves the performance of the Transformer in two code processing tasks: code completion and bug fixing.
Deep learning is at the heart of the current rise of artificial intelligence. In the field of Computer Vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas deep neural networks have
demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has recently lead to a large influx of contributions in this direction. This article presents a survey on adversarial attacks on deep learning in Computer Vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them
Deep neural language models such as BERT have enabled substantial recent advances in many natural language processing tasks. However, due to the effort and computational cost involved in their pre-training, such models are typically introduced only f
or a small number of high-resource languages such as English. While multilingual models covering large numbers of languages are available, recent work suggests monolingual training can produce better models, and our understanding of the tradeoffs between mono- and multilingual training is incomplete. In this paper, we introduce a simple, fully automated pipeline for creating language-specific BERT models from Wikipedia data and introduce 42 new such models, most for languages up to now lacking dedicated deep neural language models. We assess the merits of these models using cloze tests and the state-of-the-art UDify parser on Universal Dependencies data, contrasting performance with results using the multilingual BERT (mBERT) model. We find that the newly introduced WikiBERT models outperform mBERT in cloze tests for nearly all languages, and that UDify using WikiBERT models outperforms the parser using mBERT on average, with the language-specific models showing substantially improved performance for some languages, yet limited improvement or a decrease in performance for others. All of the methods and models introduced in this work are available under open licenses from https://github.com/turkunlp/wikibert.
Written by three experts in the field, Deep Learning is the only comprehensive book on the subject." -- Elon Musk, co-chair of OpenAI; cof-ounder and CEO of Tesla and SpaceX
Active learning has been shown to reduce annotation requirements for numerous natural language processing tasks, including semantic role labeling (SRL). SRL involves labeling argument spans for potentially multiple predicates in a sentence, which mak
es it challenging to aggregate the numerous decisions into a single score for determining new instances to annotate. In this paper, we apply two ways of aggregating scores across multiple predicates in order to choose query sentences with two methods of estimating model certainty: using the neural network's outputs and using dropout-based Bayesian Active Learning by Disagreement. We compare these methods with three passive baselines --- random sentence selection, random whole-document selection, and selecting sentences with the most predicates --- and analyse the effect these strategies have on the learning curve with respect to reducing the number of annotated sentences and predicates to achieve high performance.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
