Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOn the Difficulty of Translating Free-Order Case-Marking Languages
في صعوبة ترجمة لغات وضع علامات الترتيب الحرة
640
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
التجرخص تحديد العوامل التي تجعل لغات معينة يصعب طرازها من غيرها ضرورية للوصول إلى المساواة اللغوية في تكنولوجيات معالجة اللغة الطبيعية في المستقبل. لقد أثبتت لغات وضع علامات الترتيب الحرة، مثل اللغة الروسية أو اللاتينية أو التاميلية أكثر تحديا أكثر من لغات الطلب الثابت لمهام التنبؤ بالتحليل النحوي وتنبؤ اتفاقية الأم الفعل. في هذا العمل، نحقق ما إذا كانت هذه الفئة من اللغات أكثر صعوبة أيضا ترجمتها من قبل نماذج الترجمة الآلية الحديثة (NMT). باستخدام مجموعة متنوعة من اللغات الاصطناعية ومجموعة تحدي الترجمة المقدمة حديثا، نجد أن مرونة ترتيب الكلمات في اللغة المصدر تؤدي فقط إلى فقدان جودة NMT فقط، على الرغم من أن حجج الفعل الأساسية تصبح مستحيلة في الغموض في الجمل دون إشارات دلالية وبعد تم حل المشكلة الأخيرة بالفعل عن طريق إضافة علامات الحالة. ومع ذلك، في إعدادات الموارد المتوسطة والمنخفضة، لا تزال جودة NMT الإجمالية لغات النظام الثابت لا مثيل لها.
Abstract Identifying factors that make certain languages harder to model than others is essential to reach language equality in future Natural Language Processing technologies. Free-order case-marking languages, such as Russian, Latin, or Tamil, have proved more challenging than fixed-order languages for the tasks of syntactic parsing and subject-verb agreement prediction. In this work, we investigate whether this class of languages is also more difficult to translate by state-of-the-art Neural Machine Translation (NMT) models. Using a variety of synthetic languages and a newly introduced translation challenge set, we find that word order flexibility in the source language only leads to a very small loss of NMT quality, even though the core verb arguments become impossible to disambiguate in sentences without semantic cues. The latter issue is indeed solved by the addition of case marking. However, in medium- and low-resource settings, the overall NMT quality of fixed-order languages remains unmatched.
References used
https://aclanthology.org/
rate research
Read More
Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition, attention
can be used to locate and segment the words. We show, however, that even on monolingual data this approach is brittle. In our experiments with different input types, data sizes, and segmentation algorithms, only models trained to predict phones from words succeed in the task. Models trained to predict words from either phones or speech (i.e., the opposite direction needed to generalize to new data), yield much worse results, suggesting that attention-based segmentation is only useful in limited scenarios.
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.
This research discusses the operational integration mechanism between a seaport and
a free zone, a case study on Jebel Ali Free Zone; selecting Jebel for its high performance
and distinguished position achieved on both Arabic and International leve
ls; definitions of
the various types of free zones were introduced as well as a figure representing the
mechanism of operational integration supported by a thorough analysis of the current cargo
flow between Jebel Ali Free Zone and Port on various fields and levels, such as custom
clearance, informatics such as Tradnet , Main, Mirsal and Electronic Data Interchange, and
its role in creating such integration, a statistical hypothetical tests were conducted on the
relationship among the number of containers handled at the port and free zone , exports ,
imports and Gross Domestic Product (GDP). The research concluded the importance of
benefiting from Jebel Ali Free zone experience of integration between the seaport and free
zone.
Gross Domestic Product
imports
الواردات
المنطقة الحرة
القوانين و النظم الجمركية
المنطقة الحرة المرفئية
الميناء البحري
المنطقة الحرة فى جبل علي
الناتج المحلي الاجمالي
الصادرات غير النفطية
أعداد الحاويات المكافئة
Free Zone
Custom Laws And Regulations
Seaport Free Zone
Sea Port
Jebel Ali Free Zone
Non-Oil Exports
Number Of Containers Handled
المزيد..
Multilingual neural machine translation models typically handle one source language at a time. However, prior work has shown that translating from multiple source languages improves translation quality. Different from existing approaches on multi-sou
rce translation that are limited to the test scenario where parallel source sentences from multiple languages are available at inference time, we propose to improve multilingual translation in a more common scenario by exploiting synthetic source sentences from auxiliary languages. We train our model on synthetic multi-source corpora and apply random masking to enable flexible inference with single-source or bi-source inputs. Extensive experiments on Chinese/English-Japanese and a large-scale multilingual translation benchmark show that our model outperforms the multilingual baseline significantly by up to +4.0 BLEU with the largest improvements on low-resource or distant language pairs.
Few-shot relation extraction (FSRE) focuses on recognizing novel relations by learning with merely a handful of annotated instances. Meta-learning has been widely adopted for such a task, which trains on randomly generated few-shot tasks to learn gen
eric data representations. Despite impressive results achieved, existing models still perform suboptimally when handling hard FSRE tasks, where the relations are fine-grained and similar to each other. We argue this is largely because existing models do not distinguish hard tasks from easy ones in the learning process. In this paper, we introduce a novel approach based on contrastive learning that learns better representations by exploiting relation label information. We further design a method that allows the model to adaptively learn how to focus on hard tasks. Experiments on two standard datasets demonstrate the effectiveness of our method.
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
