arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.07027cs.CL
收藏

向预训练的Transformers添加递归以提高效率和上下文大小

Adding Recurrence to Pretrained Transformers for Improved Efficiency and Context Size

University of Chicago(芝加哥大学)

Davis Yoshida, Allyson Ettinger, Kevin Gimpel

摘要:

在过去的几年里,为下游任务微调预训练的Transformer已经成为NLP的标准方法。虽然这些模型的结果令人印象深刻,但应用它们可能非常昂贵,就像使用最新架构预训练新模型一样。我们提出了一种新的方法来应用预训练的Transformer语言模型,降低了它们在训练和推理时的内存需求。另一个好处是,我们的方法消除了大多数Transformer模型具有的固定上下文大小约束,从而允许更灵活的使用。当应用到GPT-2语言模型,我们发现,我们的方法获得更好的困惑比未修改的GPT-2模型上的PG-19和WikiText-103语料库,对于给定的计算量或内存。

英文摘要:

Fine-tuning a pretrained transformer for a downstream task has become a standard method in NLP in the last few years. While the results from these models are impressive, applying them can be extremely computationally expensive, as is pretraining new models with the latest architectures. We present a novel method for applying pretrained transformer language models which lowers their memory requirement both at training and inference time. An additional benefit is that our method removes the fixed context size constraint that most transformer models have, allowing for more flexible use. When applied to the GPT-2 language model, we find that our method attains better perplexity than an unmodified GPT-2 model on the PG-19 and WikiText-103 corpora, for a given amount of computation or memory.

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。

↑