Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEnsemble Fine-tuned mBERT for Translation Quality Estimation
الفرقة التي tuned tuned mbert لتقدير جودة الترجمة
469
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يعد تقدير الجودة (QE) مكونا هاما لسير عمل الترجمة الآلي لأنه يقيم جودة الإخراج المترجم دون الترجمات المرجعية الاستشارية.في هذه الورقة، نناقش التقديم لدينا إلى المهمة المشتركة WMT 2021 QE.إننا نشارك في المهمة الفرعية الفرعية على مستوى الجملة 2 المهام التي تتحدى المشاركين للتنبؤ بدرجة HTER من أجل جهد التحرير على مستوى الجملة.نظامنا المقترح هو مجموعة من نماذج الانحدار من بيرت (mbert) متعددة اللغات، والتي يتم إنشاؤها بواسطة ضبط صقلها على إعدادات الإدخال المختلفة.يوضح أداء قابلا للمقارنة فيما يتعلق بترابط بيرسون، وتغلب على نظام الأساس في ماي / رموز لعدة أزواج اللغة.بالإضافة إلى ذلك، نقوم بتكييف نظامنا لإعداد اللقطة الصفرية من خلال استغلال أزواج اللغة ذات الصلة بالغة والترجمات المرجعية الزائفة.
Quality Estimation (QE) is an important component of the machine translation workflow as it assesses the quality of the translated output without consulting reference translations. In this paper, we discuss our submission to the WMT 2021 QE Shared Task. We participate in Task 2 sentence-level sub-task that challenge participants to predict the HTER score for sentence-level post-editing effort. Our proposed system is an ensemble of multilingual BERT (mBERT)-based regression models, which are generated by fine-tuning on different input settings. It demonstrates comparable performance with respect to the Pearson's correlation, and beat the baseline system in MAE/ RMSE for several language pairs. In addition, we adapt our system for the zero-shot setting by exploiting target language-relevant language pairs and pseudo-reference translations.
References used
https://aclanthology.org/
rate research
Read More
This work introduces a simple regressive ensemble for evaluating machine translation quality based on a set of novel and established metrics. We evaluate the ensemble using a correlation to expert-based MQM scores of the WMT 2021 Metrics workshop. In
both monolingual and zero-shot cross-lingual settings, we show a significant performance improvement over single metrics. In the cross-lingual settings, we also demonstrate that an ensemble approach is well-applicable to unseen languages. Furthermore, we identify a strong reference-free baseline that consistently outperforms the commonly-used BLEU and METEOR measures and significantly improves our ensemble's performance.
The paper presents our submission to the WMT2021 Shared Task on Quality Estimation (QE). We participate in sentence-level predictions of human judgments and post-editing effort. We propose a glass-box approach based on attention weights extracted fro
m machine translation systems. In contrast to the previous works, we directly explore attention weight matrices without replacing them with general metrics (like entropy). We show that some of our models can be trained with a small amount of a high-cost labelled data. In the absence of training data our approach still demonstrates a moderate linear correlation, when trained with synthetic data.
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 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.
The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation (NMT) systems.
However, proposed methods for incorporating pre-trained models are non-trivial and mainly focus on BERT, which lacks a comparison of the impact that other pre-trained models may have on translation performance. In this paper, we demonstrate that simply using the output (contextualized embeddings) of a tailored and suitable bilingual pre-trained language model (dubbed BiBERT) as the input of the NMT encoder achieves state-of-the-art translation performance. Moreover, we also propose a stochastic layer selection approach and a concept of a dual-directional translation model to ensure the sufficient utilization of contextualized embeddings. In the case of without using back translation, our best models achieve BLEU scores of 30.45 for En→De and 38.61 for De→En on the IWSLT'14 dataset, and 31.26 for En→De and 34.94 for De→En on the WMT'14 dataset, which exceeds all published numbers.
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
