WEKO3
アイテム
Background Knowledge Based Multi-Stream Neural Network for Text Classification
https://tokushima-u.repo.nii.ac.jp/records/2007924
https://tokushima-u.repo.nii.ac.jp/records/200792460635169-7529-4b78-8cb7-7eadec780431
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
app_8_12_2472.pdf (2.1 MB)
|
.png)
|
| Item type | 文献 / Documents(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2020-08-21 | |||||||||||||
| アクセス権 | ||||||||||||||
| アクセス権 | open access | |||||||||||||
| 資源タイプ | ||||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||
| 資源タイプ | journal article | |||||||||||||
| 出版社版DOI | ||||||||||||||
| 識別子タイプ | DOI | |||||||||||||
| 関連識別子 | https://doi.org/10.3390/app8122472 | |||||||||||||
| 言語 | ja | |||||||||||||
| 関連名称 | 10.3390/app8122472 | |||||||||||||
| 出版タイプ | ||||||||||||||
| 出版タイプ | VoR | |||||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||||
| タイトル | ||||||||||||||
| タイトル | Background Knowledge Based Multi-Stream Neural Network for Text Classification | |||||||||||||
| 言語 | en | |||||||||||||
| 著者 |
任, 福継
× 任, 福継
WEKO
401
× Deng, Jiawen
|
|||||||||||||
| 抄録 | ||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||
| 内容記述 | 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. | |||||||||||||
| 言語 | en | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | classification algorithms | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | knowledge engineering | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | neural networks | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | machine learning | |||||||||||||
| 書誌情報 |
en : Applied Sciences 巻 8, 号 12, p. 2472, 発行日 2018-12-03 |
|||||||||||||
| 収録物ID | ||||||||||||||
| 収録物識別子タイプ | ISSN | |||||||||||||
| 収録物識別子 | 20763417 | |||||||||||||
| 出版者 | ||||||||||||||
| 出版者 | MDPI | |||||||||||||
| 言語 | en | |||||||||||||
| 権利情報 | ||||||||||||||
| 言語 | en | |||||||||||||
| 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/). | |||||||||||||
| EID | ||||||||||||||
| 識別子 | 348274 | |||||||||||||
| 識別子タイプ | URI | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
