Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHW-TSC's Participation in the WMT 2021 Efficiency Shared Task
مشاركة HW-TSC في المهمة المشتركة الكفاءة WMT 2021
320
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تقدم هذه الورقة تقديم مركز خدمات الترجمة Huawei (HW-TSC) إلى مهمة مشتركة من WMT 2021.نستكشف تقنية تقطير الطالبات على مستوى الجملة وتدريب العديد من النماذج الصغيرة التي تجد التوازن بين الكفاءة والجودة.تتميز نماذجنا بمثابة تشفير عميق ومكتشف ضحل وخفيف الوزن RNN مع طبقة SSRU.نستخدم بولت هواوي نوح، مكتبة فعالة ووزن خفيفة للاستدلال على الجهاز.الاستفادة من كمية INT8 الكمي، مشغل مصفوفة العام (GEMM) العام المعرفة ذاتيا (GEMM)، القائمة المختصرة، البحث الجشع والتخزين المؤقت، نقدم أربعة نماذج ترجمة صغيرة الحجم وكفاءة مع جودة الترجمة عالية لمسار الكمون CPU واحد.
This paper presents the submission of Huawei Translation Services Center (HW-TSC) to WMT 2021 Efficiency Shared Task. We explore the sentence-level teacher-student distillation technique and train several small-size models that find a balance between efficiency and quality. Our models feature deep encoder, shallow decoder and light-weight RNN with SSRU layer. We use Huawei Noah's Bolt, an efficient and light-weight library for on-device inference. Leveraging INT8 quantization, self-defined General Matrix Multiplication (GEMM) operator, shortlist, greedy search and caching, we submit four small-size and efficient translation models with high translation quality for the one CPU core latency track.
References used
https://aclanthology.org/
rate research
Read More
This paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT 2021 News Translation Shared Task. We participate in 7 language pairs, including Zh/En, De/En, Ja/En, Ha/En, Is/En, Hi/Bn, and Xh/Zu in both directions under t
he constrained condition. We use Transformer architecture and obtain the best performance via multiple variants with larger parameter sizes. We perform detailed pre-processing and filtering on the provided large-scale bilingual and monolingual datasets. Several commonly used strategies are used to train our models, such as Back Translation, Forward Translation, Multilingual Translation, Ensemble Knowledge Distillation, etc. Our submission obtains competitive results in the final evaluation.
This paper presents our work in WMT 2021 Quality Estimation (QE) Shared Task. We participated in all of the three sub-tasks, including Sentence-Level Direct Assessment (DA) task, Word and Sentence-Level Post-editing Effort task and Critical Error Det
ection task, in all language pairs. Our systems employ the framework of Predictor-Estimator, concretely with a pre-trained XLM-Roberta as Predictor and task-specific classifier or regressor as Estimator. For all tasks, we improve our systems by incorporating post-edit sentence or additional high-quality translation sentence in the way of multitask learning or encoding it with predictors directly. Moreover, in zero-shot setting, our data augmentation strategy based on Monte-Carlo Dropout brings up significant improvement on DA sub-task. Notably, our submissions achieve remarkable results over all tasks.
This paper presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task. We participate in the Russian-to-Chinese task under the constrained condition. We use Transformer architecture and obtain the best
performance via a variant with larger parameter sizes. We perform detailed data pre-processing and filtering on the provided large-scale bilingual data. Several strategies are used to train our models, such as Multilingual Translation, Back Translation, Forward Translation, Data Denoising, Average Checkpoint, Ensemble, Fine-tuning, etc. Our system obtains 32.5 BLEU on the dev set and 27.7 BLEU on the test set, the highest score among all submissions.
This paper describes Lingua Custodia's submission to the WMT21 shared task on machine translation using terminologies. We consider three directions, namely English to French, Russian, and Chinese. We rely on a Transformer-based architecture as a buil
ding block, and we explore a method which introduces two main changes to the standard procedure to handle terminologies. The first one consists in augmenting the training data in such a way as to encourage the model to learn a copy behavior when it encounters terminology constraint terms. The second change is constraint token masking, whose purpose is to ease copy behavior learning and to improve model generalization. Empirical results show that our method satisfies most terminology constraints while maintaining high translation quality.
The machine translation efficiency task challenges participants to make their systems faster and smaller with minimal impact on translation quality. How much quality to sacrifice for efficiency depends upon the application, so participants were encou
raged to make multiple submissions covering the space of trade-offs. In total, there were 53 submissions by 4 teams. There were GPU, single-core CPU, and multi-core CPU hardware tracks as well as batched throughput or single-sentence latency conditions. Submissions showed hundreds of millions of words can be translated for a dollar, average latency is 5--17 ms, and models fit in 7.5--150 MB.
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
