arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.08359cs.CLcs.AIcs.LG
收藏

提取语言上下文实现语言模型压缩

Distilling Linguistic Context for Language Model Compression

KAIST(韩国科学技术院);AITRICS(艾特里克斯)

Geondo Park, Gyeongman Kim, Eunho Yang

摘要:

最近语言表示学习的成功背后是一个计算昂贵和内存密集的神经网络。知识蒸馏是在资源稀缺的环境中部署如此庞大的语言模型的一种主要技术,它可以无限制地传输学习到的单个单词表示的知识。本文基于语言表征相对定位和整体语义知识含量较高的观点,提出了一种新的语言表示学习知识提取目标,即通过两种不同的表征关系:词关系和层转换关系来传递语境知识。不像其他最近的语言模型的蒸馏技术,我们的上下文蒸馏没有任何限制,教师和学生之间的架构变化。我们验证了我们的方法的有效性,具有挑战性的基准测试的语言理解任务,不仅在各种规模的架构,而且结合DynaBERT,最近提出的自适应大小修剪方法。

英文摘要:

A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce environments, transfers the knowledge on individual word representations learned without restrictions. In this paper, inspired by the recent observations that language representations are relatively positioned and have more semantic knowledge as a whole, we present a new knowledge distillation objective for language representation learning that transfers the contextual knowledge via two types of relationships across representations: Word Relation and Layer Transforming Relation. Unlike other recent distillation techniques for the language models, our contextual distillation does not have any restrictions on architectural changes between teacher and student. We validate the effectiveness of our method on challenging benchmarks of language understanding tasks, not only in architectures of various sizes, but also in combination with DynaBERT, the recently proposed adaptive size pruning method.

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。

↑