Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSearching for More Efficient Dynamic Programs
البحث عن برامج ديناميكية أكثر كفاءة
306
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
غالبا ما تنطوي النماذج الحسابية للغة البشرية على مشاكل في الحركة. على سبيل المثال، قد تهميش محلل احتمامي على العديد من الأشجار بشكل كبير لجعل التنبؤات. غالبا ما تستخدم الخوارزميات لمثل هذه المشكلات البرمجة الديناميكية وليست فريدة من نوعها دائما. يمكن أن يكون العثور على واحد مع وقت تشغيل مقارب مثالي غير محدد، ويستغرق وقتا طويلا، وعرضة خطأ. يهدف عملنا إلى أتمتة هذه العملية الشاقة. بالنظر إلى برنامج إعلاني صحيح أولي، فإننا نبحث عن تسلسل من التحولات التي تحافظ على الدلالات لتحسين وقت التشغيل قدر الإمكان. تحقيقا لهذه الغاية، وصفنا مجموعة من تحويلات البرامج، وهي مترية بسيطة لتقييم كفاءة البرنامج المحول، وإجراءات البحث المثيرة لتحسين هذه المترية. نظهر أنه في الممارسة العملية، البحث الآلي - - مثل البحث العقلي الذي يؤديه مبرمجات البشر --- يمكن العثور على تحسينات كبيرة في البرنامج الأولي. تجريبيا، نظرا لأن العديد من عمليات السرعة الموصوفة في أدب NLP قد تم اكتشافها تلقائيا من خلال نظامنا.
Computational models of human language often involve combinatorial problems. For instance, a probabilistic parser may marginalize over exponentially many trees to make predictions. Algorithms for such problems often employ dynamic programming and are not always unique. Finding one with optimal asymptotic runtime can be unintuitive, time-consuming, and error-prone. Our work aims to automate this laborious process. Given an initial correct declarative program, we search for a sequence of semantics-preserving transformations to improve its running time as much as possible. To this end, we describe a set of program transformations, a simple metric for assessing the efficiency of a transformed program, and a heuristic search procedure to improve this metric. We show that in practice, automated search---like the mental search performed by human programmers---can find substantial improvements to the initial program. Empirically, we show that many speed-ups described in the NLP literature could have been discovered automatically by our system.
References used
https://aclanthology.org/
rate research
Read More
Recent studies have shown that deep neural network-based models are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. Howeve
r, there is a lack of systematic study on comparing different defense approaches under the same attacking setting. In this paper, we seek to fill the gap of systematic studies through comprehensive researches on understanding the behavior of neural text classifiers trained by various defense methods under representative adversarial attacks. In addition, we propose an effective method to further improve the robustness of neural text classifiers against such attacks, and achieved the highest accuracy on both clean and adversarial examples on AGNEWS and IMDB datasets by a significant margin. We hope this study could provide useful clues for future research on text adversarial defense. Codes are available at https://github.com/RockyLzy/TextDefender.
This paper addresses the efficiency challenge of Neural Architecture Search (NAS) by formulating the task as a ranking problem. Previous methods require numerous training examples to estimate the accurate performance of architectures, although the ac
tual goal is to find the distinction between good'' and bad'' candidates. Here we do not resort to performance predictors. Instead, we propose a performance ranking method (RankNAS) via pairwise ranking. It enables efficient architecture search using much fewer training examples. Moreover, we develop an architecture selection method to prune the search space and concentrate on more promising candidates. Extensive experiments on machine translation and language modeling tasks show that RankNAS can design high-performance architectures while being orders of magnitude faster than state-of-the-art NAS systems.
the biological control of insects is the most safe and important
way of control, it depends on mass rearing of parasitoid, but
the ability of parasitoid become weaker after several
generations of laboratory rearing. The aim of the present study
w
as to determine the potential of Cotesia glomerata (L) in
searching and responding when it's rearing on alternative hosts
in laboratory Aporia crataegi(L),Pieris brassicae (L) and
Galleria mellonella (L). The fertilized females showed a
preference for host larvae that reared on then for the larvae
Pieris brassicae (L), so the olfactory memory in C. glomerata
(L) gets in larvae stage and continue until the emergence of
adults and lay their eggs in their hosts which reared in more
efficiently.
The range of works that can be considered as developing NLP for social good (NLP4SG) is enormous. While many of them target the identification of hate speech or fake news, there are others that address, e.g., text simplification to alleviate conseque
nces of dyslexia, or coaching strategies to fight depression. However, so far, there is no clear picture of what areas are targeted by NLP4SG, who are the actors, which are the main scenarios and what are the topics that have been left aside. In order to obtain a clearer view in this respect, we first propose a working definition of NLP4SG and identify some primary aspects that are crucial for NLP4SG, including, e.g., areas, ethics, privacy and bias. Then, we draw upon a corpus of around 50,000 articles downloaded from the ACL Anthology. Based on a list of keywords retrieved from the literature and revised in view of the task, we select from this corpus articles that can be considered to be on NLP4SG according to our definition and analyze them in terms of trends along the time line, etc. The result is a map of the current NLP4SG research and insights concerning the white spots on this map.
In this paper, we propose a simple few-shot domain adaptation paradigm for reading comprehension. We first identify the lottery subnetwork structure within the Transformer-based source domain model via gradual magnitude pruning. Then, we only fine-tu
ne the lottery subnetwork, a small fraction of the whole parameters, on the annotated target domain data for adaptation. To obtain more adaptable subnetworks, we introduce self-attention attribution to weigh parameters, beyond simply pruning the smallest magnitude parameters, which can be seen as combining structured pruning and unstructured magnitude pruning softly. Experimental results show that our method outperforms the full model fine-tuning adaptation on four out of five domains when only a small amount of annotated data available for adaptation. Moreover, introducing self-attention attribution reserves more parameters for important attention heads in the lottery subnetwork and improves the target domain model performance. Our further analyses reveal that, besides exploiting fewer parameters, the choice of subnetworks is critical to the effectiveness.
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
