DeQA: On-Device Question Answering
DeQA: On-Device Question Answering
复制标题
DOI：
10.1145/3307334.3326071
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Qingqing Cao;Noah Weber;Niranjan Balasubramanian;A. Balasubramanian
中科院分区：
文献类型：
--
作者：
Qingqing Cao;Noah Weber;Niranjan Balasubramanian;A. Balasubramanian
目前在移动设备上还没有对设备范围的问题回答的有效支持。最先进的QA模型是为云计算设计的深度学习庞然大物，运行速度极慢，需要比手机更多的内存。我们提出了DeQA，一套延迟和内存优化，使现有的QA系统完全在本地移动电话上运行。具体来说，我们设计了两个延迟优化：(1)如果进一步处理不能提高答案质量，则停止处理文档；(2)识别不依赖于问题的计算并将其移到离线状态。这些优化不依赖于QA模型内部，可以应用于几个现有的QA模型。DeQA还通过以下方式实现了一组内存优化：(i)在内存中加载部分索引，（ii）处理较小的数据单元，以及（iii）用键值数据库替换内存中的查找。我们使用DeQA将三个最先进的QA系统移植到移动设备上，并评估了三个数据集。第一个是在维基百科集合上定义的大规模SQuAD数据集。我们还创建了两个设备上的QA数据集，一个基于公开的电子邮件数据收集，另一个使用我们从两个用户那里获得的跨应用数据收集。我们的评估表明，DeQA可以在只有几百mb内存的情况下运行QA模型，并在所有三个数据集上提供至少13倍的平均加速。%，精度下降不到1%。
Today there is no effective support for device-wide question answering on mobile devices. State-of-the-art QA models are deep learning behemoths designed for the cloud which run extremely slow and require more memory than available on phones. We present DeQA, a suite of latency- and memory- optimizations that adapts existing QA systems to run completely locally on mobile phones. Specifically, we design two latency optimizations that (1) stops processing documents if further processing cannot improve answer quality, and (2) identifies computation that does not depend on the question and moves it offline. These optimizations do not depend on the QA model internals and can be applied to several existing QA models. DeQA also implements a set of memory optimizations by (i) loading partial indexes in memory, (ii) working with smaller units of data, and (iii) replacing in-memory lookups with a key-value database. We use DeQA to port three state-of-the-art QA systems to the mobile device and evaluate over three datasets. The first is a large scale SQuAD dataset defined over Wikipedia collection. We also create two on-device QA datasets, one over a publicly available email data collection and the other using a cross-app data collection we obtain from two users. Our evaluations show that DeQA can run QA models with only a few hundred MBs of memory and provides at least 13x speedup on average on the mobile phone across all three datasets.% with less than a 1% drop in accuracy.