Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOn nature and causes of observed MT errors
على الطبيعة وأسباب أخطاء MT الملاحظة
584
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يصف هذا العمل تحليل طبيعة وأسباب أخطاء MT التي لوحظها مقيمين مختلفين بموجب إرشادات لمعايير الجودة المختلفة: كفاية والفهم وعدم تحديد خليط عام من كفايته والطلاقة.نبلغ عن نتائج ثلاثة أزواج لغوية ومجالات ونظم من طراز MT.تشير النتائج الخاصة بنا إلى أنه وعلى الرغم من حقيقة أن بعض الظواهر المحددة تعتمد على المجال و / أو اللغة ويمكن اعتبار مجموعة الظواهر التالية تحديا عموما لأنظمة MT الحديثة: إعادة صياغة مجموعات الكلمات والترجمة للكلمات المصدر الغامضة والترجمةعبارات الاسم والأحساس.علاوة على ذلك، نوضح أن معيار الجودة له تأثير على تصور الخطأ.تشير النتائج الخاصة بنا إلى أن الفهم والكفايات يمكن تقييمها في وقت واحد من قبل مقيمين مختلفين، وبذلك بحيث الفهم وكمعيار جودة مهم ويمكن إدراجه في كثير من الأحيان في التقييمات البشرية.
This work describes analysis of nature and causes of MT errors observed by different evaluators under guidance of different quality criteria: adequacy and comprehension and and a not specified generic mixture of adequacy and fluency. We report results for three language pairs and two domains and eleven MT systems. Our findings indicate that and despite the fact that some of the identified phenomena depend on domain and/or language and the following set of phenomena can be considered as generally challenging for modern MT systems: rephrasing groups of words and translation of ambiguous source words and translating noun phrases and and mistranslations. Furthermore and we show that the quality criterion also has impact on error perception. Our findings indicate that comprehension and adequacy can be assessed simultaneously by different evaluators and so that comprehension and as an important quality criterion and can be included more often in human evaluations.
References used
https://aclanthology.org/
rate research
Read More
In this paper, we present the systems submitted by our team from the Institute of ICT (HEIG-VD / HES-SO) to the Unsupervised MT and Very Low Resource Supervised MT task. We first study the improvements brought to a baseline system by techniques such
as back-translation and initialization from a parent model. We find that both techniques are beneficial and suffice to reach performance that compares with more sophisticated systems from the 2020 task. We then present the application of this system to the 2021 task for low-resource supervised Upper Sorbian (HSB) to German translation, in both directions. Finally, we present a contrastive system for HSB-DE in both directions, and for unsupervised German to Lower Sorbian (DSB) translation, which uses multi-task training with various training schedules to improve over the baseline.
We revisit the topic of translation direction in the data used for training neural machine translation systems and focusing on a real-world scenario with known translation direction and imbalances in translation direction: the Canadian Hansard. Accor
ding to automatic metrics and we observe that using parallel data that was produced in the matching'' translation direction (Authentic source and translationese target) improves translation quality. In cases of data imbalance in terms of translation direction and we find that tagging of translation direction can close the performance gap. We perform a human evaluation that differs slightly from the automatic metrics and but nevertheless confirms that for this French-English dataset that is known to contain high-quality translations and authentic or tagged mixed source improves over translationese source for training.
Document-level human evaluation of machine translation (MT) has been raising interest in the community. However, little is known about the issues of using document-level methodologies to assess MT quality. In this article, we compare the inter-annota
tor agreement (IAA) scores, the effort to assess the quality in different document-level methodologies, and the issue of misevaluation when sentences are evaluated out of context.
Find sheds light on the problem perhaps more importantly, the total problems that we find in the history of philosophy , and is not a problem of nature Our research is trying to explore the meaning of the nature of the Beginnings, As we will try to,
In this research dealt with the nature of the problem of the two sides Systematic and cognitive To find out the key points of the nature of the problem when the philosophers of the seventeenth century To try to adjust the nature of the problem in its historical context As we will try in this research shed light on the relationship between nature and other problems In the philosophy of Hegel, such as the relationship , for example, between nature and logic, nature and absolute idea. Is Hegel was able to solve the problem of nature and its relationship with the various aspects of his philosophy؟ Or is it Al this problem and do so by him Kant There is also in our many other problems discussed by Hegel with nature problem.
We present the findings of the WMT2021 Shared Tasks in Unsupervised MT and Very Low Resource Supervised MT. Within the task, the community studied very low resource translation between German and Upper Sorbian, unsupervised translation between German
and Lower Sorbian and low resource translation between Russian and Chuvash, all minority languages with active language communities working on preserving the languages, who are partners in the evaluation. Thanks to this, we were able to obtain most digital data available for these languages and offer them to the task participants. In total, six teams participated in the shared task. The paper discusses the background, presents the tasks and results, and discusses best practices for the future.
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
