Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userICL's Submission to the WMT21 Critical Error Detection Shared Task
تقديم ICL إلى مهمة الكشف عن الخطأ الحرج WMT21
518
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تقدم هذه الورقة التقديمات الكلية الإمبراطورية لندن إلى المهمة المشتركة لتقدير الجودة WMT21 (QE) 3: اكتشاف الخطأ الحرج.ينشئ نهجنا على تمثيلات متدرب مسبقا عبر اللغات في نموذج تصنيف التسلسل.ونحن كذلك تحسين المصنف الأساسي من خلال (ط) إضافة عينات مرجحة للتعامل مع البيانات غير المتوازنة و (2) إدخال هندسة ميزة، حيث يتم استخراج الميزات المتعلقة بالسمية، المسماة الكيانات والمعنويات، والتي من المحتمل أن تكون مؤشرا على الأخطاء الحرجة، باستخدامالأدوات الموجودة ومتكاملة للنموذج بطرق مختلفة.نحن ندرب النماذج مع نوع واحد من الميزات في وقت واحد وفرق تلك النماذج التي تتحسن عبر المصنف الأساسي على مجموعة تطوير (dev).إن عروضنا الرسمية تحقق نتائج تنافسية للغاية، ترتيب المرتبة الثانية لثلاثة من أزواج أربعة لغات.
This paper presents Imperial College London's submissions to the WMT21 Quality Estimation (QE) Shared Task 3: Critical Error Detection. Our approach builds on cross-lingual pre-trained representations in a sequence classification model. We further improve the base classifier by (i) adding a weighted sampler to deal with unbalanced data and (ii) introducing feature engineering, where features related to toxicity, named-entities and sentiment, which are potentially indicative of critical errors, are extracted using existing tools and integrated to the model in different ways. We train models with one type of feature at a time and ensemble those models that improve over the base classifier on the development (dev) set. Our official submissions achieve very competitive results, ranking second for three out of four language pairs.
References used
https://aclanthology.org/
rate research
Read More
We submitted two uni-directional models, one for English→Icelandic direction and other for Icelandic→English direction. Our news translation system is based on the transformer-big architecture, it makes use of corpora filtering, back-translation and
forward translation applied to parallel and monolingual data alike
This paper presents the NICT Kyoto submission for the WMT'21 Quality Estimation (QE) Critical Error Detection shared task (Task 3). Our approach relies mainly on QE model pretraining for which we used 11 language pairs, three sentence-level and three
word-level translation quality metrics. Starting from an XLM-R checkpoint, we perform continued training by modifying the learning objective, switching from masked language modeling to QE oriented signals, before finetuning and ensembling the models. Results obtained on the test set in terms of correlation coefficient and F-score show that automatic metrics and synthetic data perform well for pretraining, with our submissions ranked first for two out of four language pairs. A deeper look at the impact of each metric on the downstream task indicates higher performance for token oriented metrics, while an ablation study emphasizes the usefulness of conducting both self-supervised and QE pretraining.
This paper describes Papago submission to the WMT 2021 Quality Estimation Task 1: Sentence-level Direct Assessment. Our multilingual Quality Estimation system explores the combination of Pretrained Language Models and Multi-task Learning architecture
s. We propose an iterative training pipeline based on pretraining with large amounts of in-domain synthetic data and finetuning with gold (labeled) data. We then compress our system via knowledge distillation in order to reduce parameters yet maintain strong performance. Our submitted multilingual systems perform competitively in multilingual and all 11 individual language pair settings including zero-shot.
This paper describes our work in the WMT 2021 Machine Translation using Terminologies Shared Task. We participate in the shared translation terminologies task in English to Chinese language pair. To satisfy terminology constraints on translation, we
use a terminology data augmentation strategy based on Transformer model. We used tags to mark and add the term translations into the matched sentences. We created synthetic terms using phrase tables extracted from bilingual corpus to increase the proportion of term translations in training data. Detailed pre-processing and filtering on data, in-domain finetuning and ensemble method are used in our system. Our submission obtains competitive results in the terminology-targeted evaluation.
This paper presents the JHU-Microsoft joint submission for WMT 2021 quality estimation shared task. We only participate in Task 2 (post-editing effort estimation) of the shared task, focusing on the target-side word-level quality estimation. The tech
niques we experimented with include Levenshtein Transformer training and data augmentation with a combination of forward, backward, round-trip translation, and pseudo post-editing of the MT output. We demonstrate the competitiveness of our system compared to the widely adopted OpenKiwi-XLM baseline. Our system is also the top-ranking system on the MT MCC metric for the English-German language pair.
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
