Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userWhen in Doubt: Improving Classification Performance with Alternating Normalization
عندما تكون موضع شك: تحسين أداء التصنيف مع التطبيع بالتناوب
358
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نقدم تصنيف التصنيف بتطبيع بالتناوب (CAN)، خطوة غير معالجة غير رسمية للتصنيف.يمكن أن يحسن دقة التصنيف للأمثلة الصعبة من خلال إعادة ضبط توزيع احتمالية الفئة المتوقعة باستخدام توزيعات الطبقة المتوقعة لأمثلة التحقق من الثقة عالية الثقة.يمكن أن ينطبق بسهولة على أي مصنف الاحتمالية، مع الحد الأدنى من الحساب النفقات العامة.نقوم بتحليل خصائص يمكن استخدام تجارب محاكاة، وإظهار تجريبيا فعاليتها عبر مجموعة متنوعة من مهام التصنيف.
We introduce Classification with Alternating Normalization (CAN), a non-parametric post-processing step for classification. CAN improves classification accuracy for challenging examples by re-adjusting their predicted class probability distribution using the predicted class distributions of high-confidence validation examples. CAN is easily applicable to any probabilistic classifier, with minimal computation overhead. We analyze the properties of CAN using simulated experiments, and empirically demonstrate its effectiveness across a diverse set of classification tasks.
References used
https://aclanthology.org/
rate research
Read More
UDify is the state-of-the-art language-agnostic dependency parser which is trained on a polyglot corpus of 75 languages. This multilingual modeling enables the model to generalize over unknown/lesser-known languages, thus leading to improved performa
nce on low-resource languages. In this work we used linguistic typology knowledge available in URIEL database, to improve the cross-lingual transferring ability of UDify even further.
Transfer learning based on pretraining language models on a large amount of raw data has become a new norm to reach state-of-the-art performance in NLP. Still, it remains unclear how this approach should be applied for unseen languages that are not c
overed by any available large-scale multilingual language model and for which only a small amount of raw data is generally available. In this work, by comparing multilingual and monolingual models, we show that such models behave in multiple ways on unseen languages. Some languages greatly benefit from transfer learning and behave similarly to closely related high resource languages whereas others apparently do not. Focusing on the latter, we show that this failure to transfer is largely related to the impact of the script used to write such languages. We show that transliterating those languages significantly improves the potential of large-scale multilingual language models on downstream tasks. This result provides a promising direction towards making these massively multilingual models useful for a new set of unseen languages.
We present the winning entry to the Multilingual Lexical Normalization (MultiLexNorm) shared task at W-NUT 2021 (van der Goot et al., 2021a), which evaluates lexical-normalization systems on 12 social media datasets in 11 languages. We base our solut
ion on a pre-trained byte-level language model, ByT5 (Xue et al., 2021a), which we further pre-train on synthetic data and then fine-tune on authentic normalization data. Our system achieves the best performance by a wide margin in intrinsic evaluation, and also the best performance in extrinsic evaluation through dependency parsing. The source code is released at https://github.com/ufal/multilexnorm2021 and the fine-tuned models at https://huggingface.co/ufal.
The staircase visibility concerns with the study of orthogonal polygon, one of the most important subjects which are studied is the Specification kernel of the orthogonal starshaped set. Toranzos represent a very important result in Specifying the ke
rnel of the starshaped set in the usual notion of visibility via segments, after that Breen presented an analogue to this result of the staircase visibility. She also could find a way for Specifying the kernel of starshaped orthogonal polygon when this orthogonal polygon is a simply connected.
The aim of this paper is generalizing the previous way when the orthogonal polygon is secondly connected and the bounded component for the complement is a rectangular; we will prove the following result:
Let , be secondly connected closed orthogonal polygon, and staircase starshaped set. If the boundary of the bounded component for the complement is a rectangle ,so the kernel of is either one component or two or four ones.
Network coding isone of the important researches in multi-hop wireless networks domain
and it widely participates in improving the performance of these networks, since it benefits from
the broadcasting nature of transmission processes to transmit m
ore than single packet in one
broadcasting transmission. So it achieves double use of the available bandwidth, which can
increase the throughput of the network and reduce the congestion.Our aim in this research is to
verify the improvement that network coding presents to theperformance of multi-hops wireless
Ad-hoc networks, and to study the accelerating of research process for coding chances through
constructing a virtual queues according to the packets flows that pass the node, and applying
affective manner to manage this queues.
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
