arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.13561cs.LGcs.CLstat.ML
收藏

动态局部注意的可微窗口

Differentiable Window for Dynamic Local Attention

Nanyang Technological University(南洋理工大学);Salesforce Research Asia(Salesforce亚洲研究院);Institute for Infocomm Research, A-STAR(A*STAR资讯通信研究院)

Thanh-Tung Nguyen, Xuan-Phi Nguyen, Shafiq Joty, Xiaoli Li

摘要:

我们提出了微分窗口,一个新的神经模块和通用组件的动态窗口选择。虽然普遍适用,但我们展示了一个引人注目的用例,即利用微分窗口通过在输入区域上实现更集中的注意力来改进标准注意力模块。我们提出了两种不同的可微窗口,并将它们集成在Transformer架构中的两种新颖的方式。我们评估了我们提出的方法在无数的NLP任务,包括机器翻译,情感分析,主谓一致和语言建模。我们的实验结果表明,在所有任务的一致性和相当大的改进。

英文摘要:

We propose Differentiable Window, a new neural module and general purpose component for dynamic window selection. While universally applicable, we demonstrate a compelling use case of utilizing Differentiable Window to improve standard attention modules by enabling more focused attentions over the input regions. We propose two variants of Differentiable Window, and integrate them within the Transformer architecture in two novel ways. We evaluate our proposed approach on a myriad of NLP tasks, including machine translation, sentiment analysis, subject-verb agreement and language modeling. Our experimental results demonstrate consistent and sizable improvements across all tasks.

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。

↑