Improving Minimal Gated Unit for Sequential Data

DOI DOI オープンアクセス

説明

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.

2 pages, 5 figures

収録刊行物

詳細情報 詳細情報について

問題の指摘

ページトップへ