In this paper, we propose and experiment with techniques for extreme
compression of neural natural language understanding (NLU) models, making them
suitable for execution on resource-constrained devices. We propose a
task-aware, end-to-end compression approach that performs word-embedding
compression jointly with NLU task learning. We show our results on a
large-scale, commercial NLU system trained on a varied set of intents with huge
vocabulary sizes. Our approach outperforms a range of baselines and achieves a
compression rate of 97.4% with less than 3.7% degradation in predictive
performance. Our analysis indicates that the signal from the downstream task is
important for effective compression with minimal degradation in performance.

本文提出了针对神经自然语言理解模型的极端压缩技术，并在资源受限设备上进行了实验。在任务知晓的全流程压缩方法中，我们将词嵌入压缩与 NLU 任务学习相结合，经大规模商业 NU 系统测试，实现了 97.4% 的压缩率，同时预测性能下降不到 3.7%。

面向设备的自然语言理解的极致模型压缩

Extreme Model Compression for On-device Natural Language Understanding

Common-sense and background knowledge is required to understand natural
language, but in most neural natural language understanding (NLU) systems, this
knowledge must be acquired from training corpora during learning, and then it
is static at test time. We introduce a new architecture for the dynamic
integration of explicit background knowledge in NLU models. A general-purpose
reading module reads background knowledge in the form of free-text statements
(together with task-specific text inputs) and yields refined word
representations to a task-specific NLU architecture that reprocesses the task
inputs with these representations. Experiments on document question answering
(DQA) and recognizing textual entailment (RTE) demonstrate the effectiveness
and flexibility of the approach. Analysis shows that our model learns to
exploit knowledge in a semantically appropriate way.

本文提出了一种动态集成显式背景知识的 NLU 模型，使用通用阅读模块来读取背景知识，并经过实验验证其在文档问答和文本蕴涵等任务上取得了显著的效果。