Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userIntegrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages
دمج جيل البيانات غير المدعوم في الترجمة الآلية العصبية الإشراف ذاتيا لغات الموارد المنخفضة
365
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
بالنسبة لمعظم مجموعات اللغة والبيانات الموازية إما نادرة أو غير متوفرة ببساطة.لمعالجة هذا والترجمة الآلية غير المرفوعة (UMT) باستغلال كميات كبيرة من البيانات الأحادية من خلال استخدام تقنيات توليد البيانات الاصطناعية مثل الترجمة الخلفية والتوزيع وبينما يحدد NMT (SSNMT) بشكل مرئي جمل متوازية في بيانات وقابلة للمقارنة أصغر.لهذا التاريخ، لم يتم التحقيق في تقنيات توليد بيانات UMT في SSNMT.نظهر أنه بما في ذلك تقنيات UMT في SSNMT تتفوق بشكل كبير SSNMT (يصل إلى +4.3 بلو و AF2EN) بالإضافة إلى خطوط خطوط إحصائية (+50.8 بلو) و Sybrid UMT (+51.5 بلو) على أزواج لغة ذات صلة وغير ذات صلة وغير ذات صلة.
For most language combinations and parallel data is either scarce or simply unavailable. To address this and unsupervised machine translation (UMT) exploits large amounts of monolingual data by using synthetic data generation techniques such as back-translation and noising and while self-supervised NMT (SSNMT) identifies parallel sentences in smaller comparable data and trains on them. To this date and the inclusion of UMT data generation techniques in SSNMT has not been investigated. We show that including UMT techniques into SSNMT significantly outperforms SSNMT (up to +4.3 BLEU and af2en) as well as statistical (+50.8 BLEU) and hybrid UMT (+51.5 BLEU) baselines on related and distantly-related and unrelated language pairs.
References used
https://aclanthology.org/
rate research
Read More
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.
Dravidian languages, such as Kannada and Tamil, are notoriously difficult to translate by state-of-the-art neural models. This stems from the fact that these languages are morphologically very rich as well as being low-resourced. In this paper, we fo
cus on subword segmentation and evaluate Linguistically Motivated Vocabulary Reduction (LMVR) against the more commonly used SentencePiece (SP) for the task of translating from English into four different Dravidian languages. Additionally we investigate the optimal subword vocabulary size for each language. We find that SP is the overall best choice for segmentation, and that larger dictionary sizes lead to higher translation quality.
This paper describes the participation of team oneNLP (LTRC, IIIT-Hyderabad) for the WMT 2021 task, similar language translation. We experimented with transformer based Neural Machine Translation and explored the use of language similarity for Tamil-
Telugu and Telugu-Tamil. We incorporated use of different subword configurations, script conversion and single model training for both directions as exploratory experiments.
In simultaneous machine translation, finding an agent with the optimal action sequence of reads and writes that maintain a high level of translation quality while minimizing the average lag in producing target tokens remains an extremely challenging
problem. We propose a novel supervised learning approach for training an agent that can detect the minimum number of reads required for generating each target token by comparing simultaneous translations against full-sentence translations during training to generate oracle action sequences. These oracle sequences can then be used to train a supervised model for action generation at inference time. Our approach provides an alternative to current heuristic methods in simultaneous translation by introducing a new training objective, which is easier to train than previous attempts at training the agent using reinforcement learning techniques for this task. Our experimental results show that our novel training method for action generation produces much higher quality translations while minimizing the average lag in simultaneous translation.
In this paper and we explore different techniques of overcoming the challenges of low-resource in Neural Machine Translation (NMT) and specifically focusing on the case of English-Marathi NMT. NMT systems require a large amount of parallel corpora to
obtain good quality translations. We try to mitigate the low-resource problem by augmenting parallel corpora or by using transfer learning. Techniques such as Phrase Table Injection (PTI) and back-translation and mixing of language corpora are used for enhancing the parallel data; whereas pivoting and multilingual embeddings are used to leverage transfer learning. For pivoting and Hindi comes in as assisting language for English-Marathi translation. Compared to baseline transformer model and a significant improvement trend in BLEU score is observed across various techniques. We have done extensive manual and automatic and qualitative evaluation of our systems. Since the trend in Machine Translation (MT) today is post-editing and measuring of Human Effort Reduction (HER) and we have given our preliminary observations on Translation Edit Rate (TER) vs. BLEU score study and where TER is regarded as a measure of HER.
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
