Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userArabic Compact Language Modelling for Resource Limited Devices
النمذجة باللغة العربية المدمجة لأجهزة الموارد المحدودة
397
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
اكتسب نمذجة اللغة الطبيعية الكثير من الاهتمام مؤخرا.يتم تحقيق النتائج الحالية الحالية من خلال التدريب الأول نموذج لغة كبير جدا ثم قم بضبطه على مهام متعددة.ومع ذلك، هناك القليل من العمل على أحدث نماذج لغة أكثر إحكاما للأجهزة أو التطبيقات المحدودة للمورد.ناهيك عن، وكيفية تدريب هذه النماذج بكفاءة لغوية منخفضة الموارد مثل اللغة العربية.في هذه الورقة، نحقق في كيفية تدريب هذه النماذج بطريقة مدمجة للعربية.نوضح أيضا كيف يمكن تطبيق التقطير والتجميل لإنشاء نماذج أصغر.تبين تجاربنا أن أكبر نموذج لدينا هو 2x أصغر من خط الأساس يمكن أن يحقق نتائج أفضل على مهام متعددة مع بيانات أقل بنسبة 2X لإحاطاء.
Natural language modelling has gained a lot of interest recently. The current state-of-the-art results are achieved by first training a very large language model and then fine-tuning it on multiple tasks. However, there is little work on smaller more compact language models for resource-limited devices or applications. Not to mention, how to efficiently train such models for a low-resource language like Arabic. In this paper, we investigate how such models can be trained in a compact way for Arabic. We also show how distillation and quantization can be applied to create even smaller models. Our experiments show that our largest model which is 2x smaller than the baseline can achieve better results on multiple tasks with 2x less data for pretraining.
References used
https://aclanthology.org/
rate research
Read More
Sarcasm detection is one of the top challenging tasks in text classification, particularly for informal Arabic with high syntactic and semantic ambiguity. We propose two systems that harness knowledge from multiple tasks to improve the performance of
the classifier. This paper presents the systems used in our participation to the two sub-tasks of the Sixth Arabic Natural Language Processing Workshop (WANLP); Sarcasm Detection and Sentiment Analysis. Our methodology is driven by the hypothesis that tweets with negative sentiment and tweets with sarcasm content are more likely to have offensive content, thus, fine-tuning the classification model using large corpus of offensive language, supports the learning process of the model to effectively detect sentiment and sarcasm contents. Results demonstrate the effectiveness of our approach for sarcasm detection task over sentiment analysis task.
The prominence of figurative language devices, such as sarcasm and irony, poses serious challenges for Arabic Sentiment Analysis (SA). While previous research works tackle SA and sarcasm detection separately, this paper introduces an end-to-end deep
Multi-Task Learning (MTL) model, allowing knowledge interaction between the two tasks. Our MTL model's architecture consists of a Bidirectional Encoder Representation from Transformers (BERT) model, a multi-task attention interaction module, and two task classifiers. The overall obtained results show that our proposed model outperforms its single-task and MTL counterparts on both sarcasm and sentiment detection subtasks.
Due to complex cognitive and inferential efforts involved in the manual generation of one caption per image/video input, the human annotation resources are very limited for captioning tasks. We define language resource efficient as reaching the same
performance with fewer annotated captions per input. We first study the performance degradation of caption models in different language resource settings. Our analysis of caption models with SC loss shows that the performance degradation is caused by the increasingly noisy estimation of reward and baseline with fewer language resources. To mitigate this issue, we propose to reduce the variance of noise in the baseline by generalizing the single pairwise comparison in SC loss and using multiple generalized pairwise comparisons. The generalized pairwise comparison (GPC) measures the difference between the evaluation scores of two captions with respect to an input. Empirically, we show that the model trained with the proposed GPC loss is efficient on language resource and achieves similar performance with the state-of-the-art models on MSCOCO by using only half of the language resources. Furthermore, our model significantly outperforms the state-of-the-art models on a video caption dataset that has only one labeled caption per input in the training set.
The ability to search the Web sites has become essential for many people. However many sites have problems in giving the user the needed information. Search operations are typically limited to keyword searches and do not take into consideration the u
nderlying semantics of the content.The present technologies support most languages; Though Arabic is still not well supported. One of the main application areas of Ontology technology is semantics. Although there are many tools for developing
Ontology’s in many languages, Arabic WordNet seems to be the only one that supports Arabic language. In this paper we will define the necessary steps to develop Arabic Ontology for university sites using Arabic WordNet, and check that the developed Ontology is clean.
While abstractive summarization in certain languages, like English, has already reached fairly good results due to the availability of trend-setting resources, like the CNN/Daily Mail dataset, and considerable progress in generative neural models, pr
ogress in abstractive summarization for Arabic, the fifth most-spoken language globally, is still in baby shoes. While some resources for extractive summarization have been available for some time, in this paper, we present the first corpus of human-written abstractive news summaries in Arabic, hoping to lay the foundation of this line of research for this important language. The dataset consists of more than 21 thousand items. We used this dataset to train a set of neural abstractive summarization systems for Arabic by fine-tuning pre-trained language models such as multilingual BERT, AraBERT, and multilingual BART-50. As the Arabic dataset is much smaller than e.g. the CNN/Daily Mail dataset, we also applied cross-lingual knowledge transfer to significantly improve the performance of our baseline systems. The setups included two M-BERT-based summarization models originally trained for Hungarian/English and a similar system based on M-BART-50 originally trained for Russian that were further fine-tuned for Arabic. Evaluation of the models was performed in terms of ROUGE, and a manual evaluation of fluency and adequacy of the models was also performed.
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
