One reason pretraining on self-supervised linguistic tasks is effective is that it teaches models features that are helpful for language understanding. However, we want pretrained models to learn not only to represent linguistic features, but also to use those features preferentially during fine-turning. With this goal in mind, we introduce a new English-language diagnostic set called MSGS (the Mixed Signals Generalization Set), which consists of 20 ambiguous binary classification tasks that we use to test whether a pretrained model prefers linguistic or surface generalizations during fine-tuning. We pretrain RoBERTa models from scratch on quantities of data ranging from 1M to 1B words and compare their performance on MSGS to the publicly available RoBERTa-base. We find that models can learn to represent linguistic features with little pretraining data, but require far more data to learn to prefer linguistic generalizations over surface ones. Eventually, with about 30B words of pretraining data, RoBERTa-base does demonstrate a linguistic bias with some regularity. We conclude that while self-supervised pretraining is an effective way to learn helpful inductive biases, there is likely room to improve the rate at which models learn which features matter.
翻译:关于自我监督语言任务的预先培训是有效的,其原因之一是它教授了有助于语言理解的模型特征。然而,我们希望预先培训的模式不仅能够反映语言特征,而且能够在微调期间优先使用这些特征。考虑到这一目标,我们引入了一个新的英语诊断组,称为MSGS(混合信号通用集),由20个模糊的二进制任务组成,我们用来测试预先培训的模型在微调期间是否偏爱语言或表面概括。我们从头到尾对1M至1B字的数据数量进行了罗贝塔模型的预演,并将它们在MSGS上的性能与可公开获得的ROBERTA数据库的性能进行比较。我们发现,模型可以学习用少量培训前数据来代表语言特征,但需要更多数据来学习比表面的多得多的语言概括性。最后,用大约30B字的培训前数据,罗贝塔(RoBERTA)基础确实表现出某种语言偏见。我们的结论是,虽然自我监督前培训是学习感官偏向导偏差的有效方法,但有可能改进模型的特性。