Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLike Chalk and Cheese? On the Effects of Translationese in MT Training
مثل الطباشير والجبن؟في آثار الترجمة في تدريب MT
349
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نؤيد موضوع اتجاه الترجمة في البيانات المستخدمة لتدريب أنظمة الترجمة الآلية العصبية والتركيز على سيناريو في العالم الحقيقي مع اتجاه الترجمة المعروفة والاختلالات في اتجاه الترجمة: هانزارد الكندي.وفقا للمقاييس التلقائية ونحن نلاحظ أنه باستخدام البيانات الموازية التي تم إنتاجها في "اتجاه الترجمة" المطابقة (الهدف الأصيل والترجمة) يحسن جودة الترجمة.في حالات عدم توازن البيانات من حيث اتجاه الترجمة ونتجد أن وضع العلامات على اتجاه الترجمة يمكن إغلاق فجوة الأداء.نقوم بإجراء تقييم بشري يختلف قليلا عن المقاييس التلقائية، لكنه يؤكد ذلك على هذه البيانات الفرنسية الإنجليزية المعروفة لاحتواء ترجمات عالية الجودة ومصدر مختلط أصيل أو مختار على تحسين المصدر المرتبط بالترجمة للتدريب.
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. According 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.
References used
https://aclanthology.org/
rate research
Read More
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 result
s 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.
Language is contextual as meanings of words are dependent on their contexts. Contextuality is, concomitantly, a well-defined concept in quantum mechanics where it is considered a major resource for quantum computations. We investigate whether natural
language exhibits any of the quantum mechanics' contextual features. We show that meaning combinations in ambiguous phrases can be modelled in the sheaf-theoretic framework for quantum contextuality, where they can become possibilistically contextual. Using the framework of Contextuality-by-Default (CbD), we explore the probabilistic variants of these and show that CbD-contextuality is also possible.
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 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.
Large, pre-trained transformer language models, which are pervasive in natural language processing tasks, are notoriously expensive to train. To reduce the cost of training such large models, prior work has developed smaller, more compact models whic
h achieves a significant speedup in training time while maintaining competitive accuracy to the original model on downstream tasks. Though these smaller pre-trained models have been widely adopted by the community, it is not known how well are they calibrated compared to their larger counterparts. In this paper, focusing on a wide range of tasks, we thoroughly investigate the calibration properties of pre-trained transformers, as a function of their size. We demonstrate that when evaluated in-domain, smaller models are able to achieve competitive, and often better, calibration compared to larger models, while achieving significant speedup in training time. Post-hoc calibration techniques further reduce calibration error for all models in-domain. However, when evaluated out-of-domain, larger models tend to be better calibrated, and label-smoothing instead is an effective strategy to calibrate models in this setting.
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
