ساعد ظهور نماذج التعلم المتعددة المهام (MTL) في السنوات الأخيرة دفع الشقيقة للفن في اللغة الطبيعية Un-derstanding (NLU). نعتقد بشدة أن مشاكل Thanmany NLU باللغة العربية يتم تصحيحها على جني فوائد هذه النماذج. تنتهي Tothis نقترح معيار التقييم باللغة العربية للأمم المتحدة (Alue)، بناء على 8 مهام مختارة بعناية و Lateded. لمدة خمسة من هؤلاء، نوفرو مجموعات من هذه البيانات الخاصة بتقييم القطاع الخاص للهناء من نزاهة وصلاحية معيارنا. كما نقدم مجموعة بيانات تشخيصية لتحقيق الأعمال الداخلية للبحث في الأعمال الداخلية لصالحهم. تجاربهم الأولية تظهر نماذج THOTMTL تتفوق على ThereCedCounterParts مهام. ولكن من أجل مشاركة EN-TICE من المجتمع الأوسع، نلتزم بالنشر المدربين أساسا أساسيا. ومع ذلك، فإن تحليلنا يكشف أن هذا هو الكثير من الغرفة للتحسين nlu inarabic. نأمل أن يتم تشغيل Alue جزءا في مساعدة مجتمعنا على تحقيق بعض هذه التحسينات. قام الباحثون المهتمون بدعوة إلى تقديم نتائجنا إلى المتصدرين لدينا عبر الإنترنت، ويمكن الوصول إليها علنا.
The emergence of Multi-task learning (MTL)models in recent years has helped push thestate of the art in Natural Language Un-derstanding (NLU). We strongly believe thatmany NLU problems in Arabic are especiallypoised to reap the benefits of such models. Tothis end we propose the Arabic Language Un-derstanding Evaluation Benchmark (ALUE),based on 8 carefully selected and previouslypublished tasks. For five of these, we providenew privately held evaluation datasets to en-sure the fairness and validity of our benchmark.We also provide a diagnostic dataset to helpresearchers probe the inner workings of theirmodels.Our initial experiments show thatMTL models outperform their singly trainedcounterparts on most tasks. But in order to en-tice participation from the wider community,we stick to publishing singly trained baselinesonly. Nonetheless, our analysis reveals thatthere is plenty of room for improvement inArabic NLU. We hope that ALUE will playa part in helping our community realize someof these improvements. Interested researchersare invited to submit their results to our online,and publicly accessible leaderboard.
References used
https://aclanthology.org/
Advances in English language representation enabled a more sample-efficient pre-training task by Efficiently Learning an Encoder that Classifies Token Replacements Accurately (ELECTRA). Which, instead of training a model to recover masked tokens, it
New intelligent neural network built in an expert system has been designed
to parse Arabic Language. Arabic sentences have been studied and
analyzed, also classified into new syntactical fields. Each syntactical field
consists of essential sentenc
Language models used in speech recognition are often either evaluated intrinsically using perplexity on test data, or extrinsically with an automatic speech recognition (ASR) system. The former evaluation does not always correlate well with ASR perfo
Knowing the vowels in the Hebrew language is one of the most important obstacles faced by learners of the Hebrew language, because of the complexity compared to their counterparts in the Arabic language. I have worked hard, in my research, on
Detecting offensive language on Twitter has many applications ranging from detecting/predicting bullying to measuring polarization. In this paper, we focus on building a large Arabic offensive tweet dataset. We introduce a method for building a datas