Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCUNI systems for WMT21: Multilingual Low-Resource Translation for Indo-European Languages Shared Task
أنظمة CUNI ل WMT21: الترجمة متعددة اللغات منخفضة الموارد لغات الهند الهندية المشتركة
490
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تصف هذه الورقة مهمة Charles University الفرعية للمصطلحات المهمة المشتركة للترجمة في WMT21.الهدف من هذه المهمة هو تصميم نظام يترجم مع شروط معينة بناء على قاعدة بيانات المصطلحات المقدمة، مع الحفاظ على جودة الترجمة الشاملة عالية.تنافسنا في زوج اللغة الإنجليزية الفرنسية.يعتمد نهجنا على توفير الترجمات المرغوبة إلى جانب جملة الإدخال وتدريب النموذج لاستخدام هذه المصطلحات المقدمة.نحن Lemmatize المصطلحات على حد سواء أثناء التدريب والاستدلال، للسماح للنموذج لمعرفة كيفية إنتاج الأشكال السطحية الصحيحة للكلمات، عندما تختلف عن النماذج المتوفرة في قاعدة بيانات المصطلحات.
This paper describes Charles University sub-mission for Terminology translation shared task at WMT21. The objective of this task is to design a system which translates certain terms based on a provided terminology database, while preserving high overall translation quality. We competed in English-French language pair. Our approach is based on providing the desired translations alongside the input sentence and training the model to use these provided terms. We lemmatize the terms both during the training and inference, to allow the model to learn how to produce correct surface forms of the words, when they differ from the forms provided in the terminology database.
References used
https://aclanthology.org/
rate research
Read More
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 describes Charles University sub-mission for Terminology translation Shared Task at WMT21. The objective of this task is to design a system which translates certain terms based on a provided terminology database, while preserving high over
all translation quality. We competed in English-French language pair. Our approach is based on providing the desired translations alongside the input sentence and training the model to use these provided terms. We lemmatize the terms both during the training and inference, to allow the model to learn how to produce correct surface forms of the words, when they differ from the forms provided in the terminology database. Our submission ranked second in Exact Match metric which evaluates the ability of the model to produce desired terms in the translation.
This paper describes the participation of the BSC team in the WMT2021's Multilingual Low-Resource Translation for Indo-European Languages Shared Task. The system aims to solve the Subtask 2: Wikipedia cultural heritage articles, which involves transl
ation in four Romance languages: Catalan, Italian, Occitan and Romanian. The submitted system is a multilingual semi-supervised machine translation model. It is based on a pre-trained language model, namely XLM-RoBERTa, that is later fine-tuned with parallel data obtained mostly from OPUS. Unlike other works, we only use XLM to initialize the encoder and randomly initialize a shallow decoder. The reported results are robust and perform well for all tested languages.
In this work, we investigate methods for the challenging task of translating between low- resource language pairs that exhibit some level of similarity. In particular, we consider the utility of transfer learning for translating between several Indo-
European low-resource languages from the Germanic and Romance language families. In particular, we build two main classes of transfer-based systems to study how relatedness can benefit the translation performance. The primary system fine-tunes a model pre-trained on a related language pair and the contrastive system fine-tunes one pre-trained on an unrelated language pair. Our experiments show that although relatedness is not necessary for transfer learning to work, it does benefit model performance.
This report describes Microsoft's machine translation systems for the WMT21 shared task on large-scale multilingual machine translation. We participated in all three evaluation tracks including Large Track and two Small Tracks where the former one is
unconstrained and the latter two are fully constrained. Our model submissions to the shared task were initialized with DeltaLM, a generic pre-trained multilingual encoder-decoder model, and fine-tuned correspondingly with the vast collected parallel data and allowed data sources according to track settings, together with applying progressive learning and iterative back-translation approaches to further improve the performance. Our final submissions ranked first on three tracks in terms of the automatic evaluation metric.
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
