Improving Minimal Gated Unit for Sequential Data
arXiv:1906.00748v1
Originality Synthesis-oriented
AI Analysis
This is an incremental improvement for machine translation and speech recognition tasks.
The authors tackled the problem of processing sequential data more efficiently and accurately by proposing Chrono Initializer for Minimal Gated Unit initialization, confirming its effectiveness in experiments on adding and copy tasks.
In order to obtain a model which can process sequential data related to machine translation and speech recognition faster and more accurately, we propose adopting Chrono Initializer as the initialization method of Minimal Gated Unit. We evaluated the method with two tasks: adding task and copy task. As a result of the experiment, the effectiveness of the proposed method was confirmed.