Cross-lingual transfer for low-resource Arabic language understanding

This paper explores cross-lingual transfer learning in natural language understanding (NLU), with the focus on bootstrapping Arabic from high-resource English and French languages for domain classification, intent classification, and named entity recognition tasks. We adopt a BERT-based architecture and pretrain three models using open-source Wikipedia data and large-scale commercial datasets: monolingual:Arabic, bilingual:Arabic-English, and trilingual:ArabicEnglish-French models. Additionally, we use off-the-shelf machine translator to translate internal data from source English language to the target Arabic language, in an effort to enhance transfer learning through translation. We conduct experiments that finetune the three models for NLU tasks and evaluate them on a large internal dataset. Despite the morphological, orthographical, and grammatical differences between Arabic and the source languages, transfer learning performance gains from source languages and through machine translation are achieved on a realworld Arabic test dataset in both a zeroshot setting and in a setting when the models are further finetuned on labeled data from the target language.