Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTransfer Learning with Shallow Decoders: BSC at WMT2021's Multilingual Low-Resource Translation for Indo-European Languages Shared Task
نقل التعلم مع وحدة فك التشفير الضحلة: BSC في الترجمة ذات الموارد المنخفضة لغات WMT2021 للمهمة المشتركة لغات الهند الأوروبية
241
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تصف هذه الورقة مشاركة فريق BSC في ترجمة الموارد المنخفضة لغات WMT2021 للمهمة المشتركة بين اللغات الهندية الأوروبية.يهدف النظام إلى حل التتبع الفرعي 2: مقالات التراث الثقافي ويكيبيديا، والتي تنطوي على الترجمة في أربع لغات رومانسية: الكاتالونية والإيطالية والوكر والرومانية.النظام المقدم هو نموذج الترجمة شبه الإشراف متعدد اللغات.إنه يستند إلى نموذج لغة مدرب مسبقا، وهما XLM-Roberta، وهو ما يتم ضبطه في وقت لاحق مع البيانات الموازية التي تم الحصول عليها في الغالب من OPUS.على عكس الأعمال الأخرى، نستخدم XLM فقط لتهيئة التشفير والتهيئة بشكل عشوائي فك تشفير ضحلة.النتائج المبلغ عنها قوية وأداء جيدا لجميع اللغات التي تم اختبارها.
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 translation 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.
References used
https://aclanthology.org/
rate research
Read More
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.
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.
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 paper presents the work in progress toward the creation of a family of WordNets for Sanskrit, Ancient Greek, and Latin. Building on previous attempts in the field, we elaborate these efforts bridging together WordNet relational semantics with th
eories of meaning from Cognitive Linguistics. We discuss some of the innovations we have introduced to the WordNet architecture, to better capture the polysemy of words, as well as Indo-European language family-specific features. We conclude the paper framing our work within the larger picture of resources available for ancient languages and showing that WordNet-backed search tools have the potential to re-define the kinds of questions that can be asked of ancient language corpora.
We present the findings of the LoResMT 2021 shared task which focuses on machine translation (MT) of COVID-19 data for both low-resource spoken and sign languages. The organization of this task was conducted as part of the fourth workshop on technolo
gies for machine translation of low resource languages (LoResMT). Parallel corpora is presented and publicly available which includes the following directions: English↔Irish, English↔Marathi, and Taiwanese Sign language↔Traditional Chinese. Training data consists of 8112, 20933 and 128608 segments, respectively. There are additional monolingual data sets for Marathi and English that consist of 21901 segments. The results presented here are based on entries from a total of eight teams. Three teams submitted systems for English↔Irish while five teams submitted systems for English↔Marathi. Unfortunately, there were no systems submissions for the Taiwanese Sign language↔Traditional Chinese task. Maximum system performance was computed using BLEU and follow as 36.0 for English--Irish, 34.6 for Irish--English, 24.2 for English--Marathi, and 31.3 for Marathi--English.
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
