直近一年間の累計
アクセス数 : ?
ダウンロード数 : ?
ID 114992
著者
Deng, Jiawen Tokushima University
キーワード
classification algorithms
knowledge engineering
neural networks
machine learning
資料タイプ
学術雑誌論文
抄録
As a foundation and typical task in natural language processing, text classification has been widely applied in many fields. However, as the basis of text classification, most existing corpus are imbalanced and often result in the classifier tending its performance to those categories with more texts. In this paper, we propose a background knowledge based multi-stream neural network to make up for the imbalance or insufficient information caused by the limitations of training corpus. The multi-stream network mainly consists of the basal stream, which retained original sequence information, and background knowledge based streams. Background knowledge is composed of keywords and co-occurred words which are extracted from external corpus. Background knowledge based streams are devoted to realizing supplemental information and reinforce basal stream. To better fuse the features extracted from different streams, early-fusion and two after-fusion strategies are employed. According to the results obtained from both Chinese corpus and English corpus, it is demonstrated that the proposed background knowledge based multi-stream neural network performs well in classification tasks.
掲載誌名
Applied Sciences
ISSN
20763417
出版者
MDPI
8
12
開始ページ
2472
発行日
2018-12-03
権利情報
© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
EDB ID
出版社版DOI
出版社版URL
フルテキストファイル
言語
eng
著者版フラグ
出版社版
部局
理工学系