BERT-based models are currently used for solving nearly all Natural Language Processing (NLP) tasks and most often achieve state-of-the-art results. Therefore, the NLP community conducts extensive research on understanding these models, but above all on designing effective and efficient training procedures. Several ablation studies investigating how to train BERT-like models have been carried out, but the vast majority of them concerned only the English language. A training procedure designed for English does not have to be universal and applicable to other especially typologically different languages. Therefore, this paper presents the first ablation study focused on Polish, which, unlike the isolating English language, is a fusional language. We design and thoroughly evaluate a pretraining procedure of transferring knowledge from multilingual to monolingual BERT-based models. In addition to multilingual model initialization, other factors that possibly influence pretraining are also explored, i.e. training objective, corpus size, BPE-Dropout, and pretraining length. Based on the proposed procedure, a Polish BERT-based language model -- HerBERT -- is trained. This model achieves state-of-the-art results on multiple downstream tasks.
翻译:目前,基于BERT的模型用于解决几乎所有的自然语言处理(NLP)任务,而且往往实现最先进的成果。因此,NLP社区对理解这些模型进行了广泛的研究,但首先在设计有效和高效的培训程序方面进行了广泛的研究。已经开展了几项研究,调查如何培训BERT类似的模型,但绝大多数研究都只涉及英语。为英语设计的培训程序不一定是普遍性的,也不适用于其他特别类型不同的语言。因此,本文件介绍了第一个侧重于波兰语的模拟研究,与孤立的英语不同,波兰语是一种混合语言。我们设计并彻底评估了将知识从多种语言向单一语言的BERT模式转让的培训前程序。除了多语言模型初始化外,还探讨了可能影响培训前的其他因素,即培训目标、运动规模、BPE-Dropout以及培训前的长度。根据拟议的程序,对波兰的BERT语言模型 -- HerBERT -- 进行了培训。该模型在多个下游任务上实现了最先进的结果。