Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTenTrans High-Performance Inference Toolkit for WMT2021 Efficiency Task
TENTRANS مجموعة أدوات الاستدلال عالية الأداء لمهمة كفاءة WMT2021
360
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تصف الورقة توضيحات TENTRANS إلى المهمة المشتركة ل WMT 2021 المشتركة.نستكشف تدريب مجموعة متنوعة من نماذج محولات الصغار الأصغر باستخدام إعداد المعلمين - طالب.يتم تدريب نموذجنا من خلال منصة تدريب متعددة اللغات المتطورة ذاتية اللغات ذاتية اللغويةونحن نطلق أيضا مجموعة أدوات الاستدلال عالية الأداء مفتوح المصدر لنماذج المحولات والمكتب في C ++ بالكامل.يتم بناء جميع التحسينات الإضافية على رأس محرك الاستدلال بما في ذلك التخزين المؤقت للانتباه، نواة الانصهار، والتوقف المبكر، والعديد من التحسينات الأخرى.في عمليات التقديمات الخاصة بنا، يمكن أن يترجم الأسرع النظام الأسرع أكثر من 22000 رموز في الثانية مع TESLA P4 واحدة مع الحفاظ على 38.36 بلو على EN-DE NEWSTEST2019.تتوفر نماذجنا المدربة ومزيد من التفاصيل في أمثلة المنافسة التي تخدمها Tentrans.
The paper describes the TenTrans's submissions to the WMT 2021 Efficiency Shared Task. We explore training a variety of smaller compact transformer models using the teacher-student setup. Our model is trained by our self-developed open-source multilingual training platform TenTrans-Py. We also release an open-source high-performance inference toolkit for transformer models and the code is written in C++ completely. All additional optimizations are built on top of the inference engine including attention caching, kernel fusion, early-stop, and several other optimizations. In our submissions, the fastest system can translate more than 22,000 tokens per second with a single Tesla P4 while maintaining 38.36 BLEU on En-De newstest2019. Our trained models and more details are available in TenTrans-Decoding competition examples.
References used
https://aclanthology.org/
rate research
Read More
Transformer and its variants have achieved great success in natural language processing. Since Transformer models are huge in size, serving these models is a challenge for real industrial applications. In this paper, we propose , a highly efficient i
nference library for models in the Transformer family. includes a series of GPU optimization techniques to both streamline the computation of Transformer layers and reduce memory footprint. supports models trained using PyTorch and Tensorflow. Experimental results on standard machine translation benchmarks show that achieves up to 14x speedup compared with TensorFlow and 1.4x speedup compared with , a concurrent CUDA implementation. The code will be released publicly after the review.
In this paper, we present our submission to Shared Metrics Task: RoBLEURT (Robustly Optimizing the training of BLEURT). After investigating the recent advances of trainable metrics, we conclude several aspects of vital importance to obtain a well-per
formed metric model by: 1) jointly leveraging the advantages of source-included model and reference-only model, 2) continuously pre-training the model with massive synthetic data pairs, and 3) fine-tuning the model with data denoising strategy. Experimental results show that our model reaching state-of-the-art correlations with the WMT2020 human annotations upon 8 out of 10 to-English language pairs.
This paper describes TenTrans' submission to WMT21 Multilingual Low-Resource Translation shared task for the Romance language pairs. This task focuses on improving translation quality from Catalan to Occitan, Romanian and Italian, with the assistance
of related high-resource languages. We mainly utilize back-translation, pivot-based methods, multilingual models, pre-trained model fine-tuning, and in-domain knowledge transfer to improve the translation quality. On the test set, our best-submitted system achieves an average of 43.45 case-sensitive BLEU scores across all low-resource pairs. Our data, code, and pre-trained models used in this work are available in TenTrans evaluation examples.
This Paper Attempts to study the latest advancements in High Performance Computing Technologies, Which Provides suitable environments, Solid infrastructure, Software and Hardware Components, allowing Scientists and Researchers to solve Math, Biology,
Machine Learning, Physics Simulations, and numerous other problems, Allowing significant breakthroughs in these fields.
We present an open-source toolkit for Danish Natural Language Processing, enabling easy access to Danish NLP's latest advancements. The toolkit features wrapper-functions for loading models and datasets in a unified way using third-party NLP framewor
ks. The toolkit is developed to enhance community building, understanding the need from industry and knowledge sharing. As an example of this, we present Angry Tweets: An Annotation Game to create awareness of Danish NLP and create a new sentiment-annotated dataset.
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
