arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.03356cs.LGcs.CLstat.ML
收藏

Transformers需要深度远程存储器吗

Do Transformers Need Deep Long-Range Memory

DeepMind;UCL(伦敦大学学院)

Jack W. Rae, Ali Razavi

摘要:

深度注意力模型已经在许多领域推进了序列数据的建模。特别是对于语言建模,Transformer-XL --一个增强了过去激活的长距离记忆的Transformer--在各种经过充分研究的基准测试中被证明是最先进的。Transformer-XL在网络的每一层都集成了一个远程内存,这使得它的状态比RNN的前辈大数千倍。但尚不清楚这是否必要。我们进行了一组干预,以表明可以通过减少6倍的长距离记忆来获得相当的性能,并且可以通过限制网络较低层的注意力范围来获得更好的性能。

英文摘要:

Deep attention models have advanced the modelling of sequential data across many domains. For language modelling in particular, the Transformer-XL -- a Transformer augmented with a long-range memory of past activations -- has been shown to be state-of-the-art across a variety of well-studied benchmarks. The Transformer-XL incorporates a long-range memory at every layer of the network, which renders its state to be thousands of times larger than RNN predecessors. However it is unclear whether this is necessary. We perform a set of interventions to show that comparable performance can be obtained with 6X fewer long range memories and better performance can be obtained by limiting the range of attention in lower layers of the network.

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。

↑