Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userArabicTransformer: Efficient Large Arabic Language Model with Funnel Transformer and ELECTRA Objective
Arabictransformer: نموذج اللغة العربي الكبير الفعال مع محول القمع وهدف Electra
141
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تظهر النماذج المسبقة للتدريب المستندة إلى المحولات مثل Bert و Electra حول مجموعة من كورسيا العربية، التي أظهرها كل من أرابيرت وأريكيكترا، نتيجة مثيرة للإعجاب في مهام المصب.ومع ذلك، فإن نماذج اللغة المستندة إلى المحولات قبل التدريب هي باهظة الثمن، خاصة بالنسبة للنماذج الكبيرة.في الآونة الأخيرة، تناول محول القمع التكرار المتسلسل داخل بنية المحولات من خلال ضغط تسلسل الدول المخفية، مما يؤدي إلى انخفاض كبير في تكلفة ما قبل التدريب.تدرس هذه الورقة تجريبية أداء وكفاءة بناء نموذج اللغة العربية مع محول القمع وهناك هدف Electra.نجد أن نموذجنا يحقق نتائج أحدث النتائج على العديد من المهام المصب العربية على الرغم من استخدام موارد حسابية أقل مقارنة بالنماذج الأخرى القائمة على بيرت.
Pre-training Transformer-based models such as BERT and ELECTRA on a collection of Arabic corpora, demonstrated by both AraBERT and AraELECTRA, shows an impressive result on downstream tasks. However, pre-training Transformer-based language models is computationally expensive, especially for large-scale models. Recently, Funnel Transformer has addressed the sequential redundancy inside Transformer architecture by compressing the sequence of hidden states, leading to a significant reduction in the pre-training cost. This paper empirically studies the performance and efficiency of building an Arabic language model with Funnel Transformer and ELECTRA objective. We find that our model achieves state-of-the-art results on several Arabic downstream tasks despite using less computational resources compared to other BERT-based models.
References used
https://aclanthology.org/
rate research
Read More
Recently, domain shift, which affects accuracy due to differences in data between source and target domains, has become a serious issue when using machine learning methods to solve natural language processing tasks. With additional pretraining and fi
ne-tuning using a target domain corpus, pretraining models such as BERT (Bidirectional Encoder Representations from Transformers) can address this issue. However, the additional pretraining of the BERT model is difficult because it requires significant computing resources. The efficiently learning an encoder that classifies token replacements accurately (ELECTRA) pretraining model replaces the BERT pretraining method's masked language modeling with a method called replaced token detection, which improves the computational efficiency and allows the additional pretraining of the model to a practical extent. Herein, we propose a method for addressing the computational efficiency of pretraining models in domain shift by constructing an ELECTRA pretraining model on a Japanese dataset and additional pretraining this model in a downstream task using a corpus from the target domain. We constructed a pretraining model for ELECTRA in Japanese and conducted experiments on a document classification task using data from Japanese news articles. Results show that even a model smaller than the pretrained model performs equally well.
Enabling empathetic behavior in Arabic dialogue agents is an important aspect of building human-like conversational models. While Arabic Natural Language Processing has seen significant advances in Natural Language Understanding (NLU) with language m
odels such as AraBERT, Natural Language Generation (NLG) remains a challenge. The shortcomings of NLG encoder-decoder models are primarily due to the lack of Arabic datasets suitable to train NLG models such as conversational agents. To overcome this issue, we propose a transformer-based encoder-decoder initialized with AraBERT parameters. By initializing the weights of the encoder and decoder with AraBERT pre-trained weights, our model was able to leverage knowledge transfer and boost performance in response generation. To enable empathy in our conversational model, we train it using the ArabicEmpatheticDialogues dataset and achieve high performance in empathetic response generation. Specifically, our model achieved a low perplexity value of 17.0 and an increase in 5 BLEU points compared to the previous state-of-the-art model. Also, our proposed model was rated highly by 85 human evaluators, validating its high capability in exhibiting empathy while generating relevant and fluent responses in open-domain settings.
Adapters are light-weight modules that allow parameter-efficient fine-tuning of pretrained models. Specialized language and task adapters have recently been proposed to facilitate cross-lingual transfer of multilingual pretrained models (Pfeiffer et
al., 2020b). However, this approach requires training a separate language adapter for every language one wishes to support, which can be impractical for languages with limited data. An intuitive solution is to use a related language adapter for the new language variety, but we observe that this solution can lead to sub-optimal performance. In this paper, we aim to improve the robustness of language adapters to uncovered languages without training new adapters. We find that ensembling multiple existing language adapters makes the fine-tuned model significantly more robust to other language varieties not included in these adapters. Building upon this observation, we propose Entropy Minimized Ensemble of Adapters (EMEA), a method that optimizes the ensemble weights of the pretrained language adapters for each test sentence by minimizing the entropy of its predictions. Experiments on three diverse groups of language varieties show that our method leads to significant improvements on both named entity recognition and part-of-speech tagging across all languages.
The rapid rise of online social networks like YouTube, Facebook, Twitter allows people to express their views more widely online. However, at the same time, it can lead to an increase in conflict and hatred among consumers in the form of freedom of s
peech. Therefore, it is essential to take a positive strengthening method to research on encouraging, positive, helping, and supportive social media content. In this paper, we describe a Transformer-based BERT model for Hope speech detection for equality, diversity, and inclusion, submitted for LT-EDI-2021 Task 2. Our model achieves a weighted averaged f1-score of 0.93 on the test set.
Task-oriented conversational systems often use dialogue state tracking to represent the user's intentions, which involves filling in values of pre-defined slots. Many approaches have been proposed, often using task-specific architectures with special
-purpose classifiers. Recently, good results have been obtained using more general architectures based on pretrained language models. Here, we introduce a new variation of the language modeling approach that uses schema-driven prompting to provide task-aware history encoding that is used for both categorical and non-categorical slots. We further improve performance by augmenting the prompting with schema descriptions, a naturally occurring source of in-domain knowledge. Our purely generative system achieves state-of-the-art performance on MultiWOZ 2.2 and achieves competitive performance on two other benchmarks: MultiWOZ 2.1 and M2M. The data and code will be available at https://github.com/chiahsuan156/DST-as-Prompting.
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
