Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAttentive fine-tuning of Transformers for Translation of low-resourced languages @LoResMT 2021
التهاب الدقيقة من محولات الترجمة لترجمة لغات منخفضة الموارد Lolorsmt 2021
297
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تقارير هذه الورقة أنظمة الترجمة الآلية المقدمة من فريق IIITT للغة الإنجليزية → أزواج اللغة المهاراتية والإنجليزية أزواج LORESMT 2021 المشاركة المشتركة.تركز المهمة على الحصول على ترجمات استثنائية لغات منخفضة بالموارد منخفضة إلى حد ما مثل الأيرلندية والماراثية.نحن نايت Tune Endertrans، نموذج NMT متعدد اللغات مسبقا للغة الإنجليزية → Marathi، باستخدام Corpus الموازي الخارجي كمدخل للتدريب الإضافي.لقد استخدمنا نموذج English Helsinki-NLP Opus Mt للزواج باللغة الأخير.تؤدي نهجنا إلى نتائج واعدة نسبيا على مقاييس بلو.تحت اسم الفريق IIITT، تصنيف أنظمتنا في المرتبة 1، 1، و 2 باللغة الإنجليزية → الماراثي، الأيرلندية → الإنجليزية، والإنجليزية → الأيرلندية على التوالي.يتم نشر رموز أنظمتنا 1.
This paper reports the Machine Translation (MT) systems submitted by the IIITT team for the English→Marathi and English⇔Irish language pairs LoResMT 2021 shared task. The task focuses on getting exceptional translations for rather low-resourced languages like Irish and Marathi. We fine-tune IndicTrans, a pretrained multilingual NMT model for English→Marathi, using external parallel corpus as input for additional training. We have used a pretrained Helsinki-NLP Opus MT English⇔Irish model for the latter language pair. Our approaches yield relatively promising results on the BLEU metrics. Under the team name IIITT, our systems ranked 1, 1, and 2 in English→Marathi, Irish→English, and English→Irish respectively. The codes for our systems are published1 .
References used
https://aclanthology.org/
rate research
Read More
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.
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.
Pretrained multilingual language models have been shown to work well on many languages for a variety of downstream NLP tasks. However, these models are known to require a lot of training data. This consequently leaves out a huge percentage of the wor
ld's languages as they are under-resourced. Furthermore, a major motivation behind these models is that lower-resource languages benefit from joint training with higher-resource languages. In this work, we challenge this assumption and present the first attempt at training a multilingual language model on only low-resource languages. We show that it is possible to train competitive multilingual language models on less than 1 GB of text. Our model, named AfriBERTa, covers 11 African languages, including the first language model for 4 of these languages. Evaluations on named entity recognition and text classification spanning 10 languages show that our model outperforms mBERT and XLM-Rin several languages and is very competitive overall. Results suggest that our small data'' approach based on similar languages may sometimes work better than joint training on large datasets with high-resource languages. Code, data and models are released at https://github.com/keleog/afriberta.
Data-to-text (D2T) generation in the biomedical domain is a promising - yet mostly unexplored - field of research. Here, we apply neural models for D2T generation to a real-world dataset consisting of package leaflets of European medicines. We show t
hat fine-tuned transformers are able to generate realistic, multi-sentence text from data in the biomedical domain, yet have important limitations. We also release a new dataset (BioLeaflets) for benchmarking D2T generation models in the biomedical domain.
This paper describes the submission to the IWSLT 2021 Low-Resource Speech Translation Shared Task by IMS team. We utilize state-of-the-art models combined with several data augmentation, multi-task and transfer learning approaches for the automatic s
peech recognition (ASR) and machine translation (MT) steps of our cascaded system. Moreover, we also explore the feasibility of a full end-to-end speech translation (ST) model in the case of very constrained amount of ground truth labeled data. Our best system achieves the best performance among all submitted systems for Congolese Swahili to English and French with BLEU scores 7.7 and 13.7 respectively, and the second best result for Coastal Swahili to English with BLEU score 14.9.
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
