arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.11995cs.CL
收藏

预训练没有人类语言的语言模型

Pre-Training a Language Model Without Human Language

National Taiwan University(台湾大学)

Cheng-Han Chiang, Hung-yi Lee

摘要:

在本文中,我们研究了预训练数据的内在性质如何有助于微调下游性能。为此,我们在几个具有特定特征的语料库上预训练不同的基于transformer的掩码语言模型,并在GLUE基准测试中微调这些语言模型。我们发现,在非结构化数据上预先训练的模型在下游任务上击败了那些直接从头开始训练的模型。我们的研究结果还表明,对结构化数据进行预训练并不总是使模型获得可以转移到自然语言下游任务的能力。令我们非常惊讶的是,我们发现在某些非人类语言数据上进行预训练,使GLUE的性能接近在另一种非英语语言上进行预训练的性能。

英文摘要:

In this paper, we study how the intrinsic nature of pre-training data contributes to the fine-tuned downstream performance. To this end, we pre-train different transformer-based masked language models on several corpora with certain features, and we fine-tune those language models on GLUE benchmarks. We find that models pre-trained on unstructured data beat those trained directly from scratch on downstream tasks. Our results also show that pre-training on structured data does not always make the model acquire ability that can be transferred to natural language downstream tasks. To our great astonishment, we uncover that pre-training on certain non-human language data gives GLUE performance close to performance pre-trained on another non-English language.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑