Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNeural Machine Translation in Low-Resource Setting: a Case Study in English-Marathi Pair
الترجمة الآلية العصبية في إعداد الموارد المنخفضة: دراسة حالة في زوج اللغة الإنجليزية الماراثي
396
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذه الورقة ونحن نستكشف تقنيات مختلفة للتغلب على تحديات الموارد المنخفضة في الترجمة الآلية العصبية (NMT) وتركز على وجه التحديد على حالة اللغة الإنجليزية الماراثية NMT. تتطلب أنظمة NMT كمية كبيرة من كورسا الموازية للحصول على ترجمات ذات نوعية جيدة. نحاول تخفيف مشكلة الموارد المنخفضة عن طريق زيادة Corpora الموازية أو باستخدام تعلم النقل. تستخدم تقنيات مثل حقن الجدول العبارة (PTI) والترجمة الخلفي وخلط لغة اللغة لتعزيز البيانات الموازية؛ في حين أن المظلات المحورية والمحسبات متعددة اللغات تستخدم للاستفادة من تعلم التحويل. بالنسبة للمحور المحوري، تأتي الهندية في اللغة المساعدة للترجمة الإنجليزية المهاراتية. بالمقارنة مع نموذج محول الأساس، يلاحظ اتجاه تحسن كبير في درجة بلو عبر تقنيات مختلفة. لقد قمنا بإجراء تقييم واسع النطاق والتولي والنوعي لأنظمنا. نظرا لأن الاتجاه في الترجمة الآلية (MT) اليوم هو ما بعد التحرير وقياس الحد من الجهود البشرية (لها)، ونعطينا ملاحظاتنا الأولية لمعدل تحرير الترجمة (TER) مقابل دراسة درجة بلو وحيث يعتبر TER كتدبير لها.
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.
References used
https://aclanthology.org/
rate research
Read More
In this paper, we (team - oneNLP-IIITH) describe our Neural Machine Translation approaches for English-Marathi (both direction) for LoResMT-20211 . We experimented with transformer based Neural Machine Translation and explored the use of different li
nguistic features like POS and Morph on subword unit for both English-Marathi and Marathi-English. In addition, we have also explored forward and backward translation using web-crawled monolingual data. We obtained 22.2 (overall 2 nd) and 31.3 (overall 1 st) BLEU scores for English-Marathi and Marathi-English on respectively
Recent advances in Unsupervised Neural Machine Translation (UNMT) has minimized the gap between supervised and unsupervised machine translation performance for closely related language-pairs. However and the situation is very different for distant la
nguage pairs. Lack of overlap in lexicon and low syntactic similarity such as between English and IndoAryan languages leads to poor translation quality in existing UNMT systems. In this paper and we show that initialising the embedding layer of UNMT models with cross-lingual embeddings leads to significant BLEU score improvements over existing UNMT models where the embedding layer weights are randomly initialized. Further and freezing the embedding layer weights leads to better gains compared to updating the embedding layer weights during training. We experimented using Masked Sequence to Sequence (MASS) and Denoising Autoencoder (DAE) UNMT approaches for three distant language pairs. The proposed cross-lingual embedding initialization yields BLEU score improvement of as much as ten times over the baseline for English-Hindi and English-Bengali and English-Gujarati. Our analysis shows that initialising embedding layer with static cross-lingual embedding mapping is essential for training of UNMT models for distant language-pairs.
The neural machine translation approach has gained popularity in machine translation because of its context analysing ability and its handling of long-term dependency issues. We have participated in the WMT21 shared task of similar language translati
on on a Tamil-Telugu pair with the team name: CNLP-NITS. In this task, we utilized monolingual data via pre-train word embeddings in transformer model based neural machine translation to tackle the limitation of parallel corpus. Our model has achieved a bilingual evaluation understudy (BLEU) score of 4.05, rank-based intuitive bilingual evaluation score (RIBES) score of 24.80 and translation edit rate (TER) score of 97.24 for both Tamil-to-Telugu and Telugu-to-Tamil translations respectively.
The widespread presence of offensive language on social media motivated the development of systems capable of recognizing such content automatically. Apart from a few notable exceptions, most research on automatic offensive language identification ha
s dealt with English. To address this shortcoming, we introduce MOLD, the Marathi Offensive Language Dataset. MOLD is the first dataset of its kind compiled for Marathi, thus opening a new domain for research in low-resource Indo-Aryan languages. We present results from several machine learning experiments on this dataset, including zero-short and other transfer learning experiments on state-of-the-art cross-lingual transformers from existing data in Bengali, English, and Hindi.
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.
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
