论文标题
探索了解英语动词课程和大型预训练语言模型的交替
Probing for Understanding of English Verb Classes and Alternations in Large Pre-trained Language Models
论文作者
论文摘要
我们研究了Levin（1993）所述的动词交替类在多大程度上使用大型预训练的语言模型（PLM）的嵌入，例如Bert，Roberta，Electra和Deberta，使用选择性构建的词语和句子级别的预测任务。我们遵循并扩展了Kann等人的实验。 （2019年），旨在探测静态嵌入是否编码动词的框架选择性。在单词和句子级别上，我们发现来自PLM的上下文嵌入不仅超过了非上下文的嵌入，而且在大多数交替类中的任务上达到了惊人的高精度。此外，我们发现有证据表明，与所有探测任务中的较低层相比，PLM的中间层平均得分更好。
We investigate the extent to which verb alternation classes, as described by Levin (1993), are encoded in the embeddings of Large Pre-trained Language Models (PLMs) such as BERT, RoBERTa, ELECTRA, and DeBERTa using selectively constructed diagnostic classifiers for word and sentence-level prediction tasks. We follow and expand upon the experiments of Kann et al. (2019), which aim to probe whether static embeddings encode frame-selectional properties of verbs. At both the word and sentence level, we find that contextual embeddings from PLMs not only outperform non-contextual embeddings, but achieve astonishingly high accuracies on tasks across most alternation classes. Additionally, we find evidence that the middle-to-upper layers of PLMs achieve better performance on average than the lower layers across all probing tasks.
