Pre-trained language models (LMs) are currently integral to many natural language processing systems. Although multilingual LMs were also introduced to serve many languages, these have limitations such as being costly at inference time and the size and diversity of non-English data involved in their pre-training. We remedy these issues for a collection of diverse Arabic varieties by introducing two powerful deep bidirectional transformer-based models, ARBERT and MARBERT. To evaluate our models, we also introduce ARLUE, a new benchmark for multi-dialectal Arabic language understanding evaluation. ARLUE is built using 42 datasets targeting six different task clusters, allowing us to offer a series of standardized experiments under rich conditions. When fine-tuned on ARLUE, our models collectively achieve new state-of-the-art results across the majority of tasks (37 out of 48 classification tasks, on the 42 datasets). Our best model acquires the highest ARLUE score (77.40) across all six task clusters, outperforming all other models including XLM-R Large (~ 3.4 x larger size). Our models are publicly available at https://github.com/UBC-NLP/marbert and ARLUE will be released through the same repository.
翻译:培训前语言模型(LMS)目前是许多自然语言处理系统的组成部分,虽然引入多语言LMS是为了为多种语言服务,但也有多种语言的局限性,例如,在测试前的训练中,推断时间费用昂贵,非英语数据的规模和多样性也昂贵。我们通过采用两个强大的双向变压器模型(ARBERT和MARBERT)来解决这些问题,以收集多种阿拉伯品种。为了评估我们的模型,我们还引入了AARLUE,这是多种阿拉伯语理解评估的新基准。AARLUE是使用针对六个不同任务组群的42个数据集建立的,使我们能够在丰富的条件下提供一系列标准化实验。在对ARLUE进行微调时,我们的模式在大多数任务(48个分类任务中的37个,在42个数据集上)中集体实现新的最新结果。我们的最佳模型获得所有六个任务组的最高ARLUE评分(77.40),表现优于包括XLM-Rig在内的所有其他模型(~3.4x更大的大小)。我们的模型将在https://github/UBC benalbert.