WEKO3
アイテム
Automatic Stopword Generation Based on Attention for Document Classification Using Neural Networks
https://ipsj.ixsq.nii.ac.jp/records/233828
https://ipsj.ixsq.nii.ac.jp/records/233828e42acb3d-d3ff-4aa9-8b8c-7ce886465c70
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-TOD1702007.pdf (793.0 kB)
2026年4月23日からダウンロード可能です。
|
Copyright (c) 2024 by the Information Processing Society of Japan
|
|
| 非会員：¥0, IPSJ:学会員：¥0, DBS:会員：¥0, IFAT:会員：¥0, DLIB:会員：¥0 | ||
| Item type | Trans(1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2024-04-23 | |||||||||
| タイトル | ||||||||||
| タイトル | Automatic Stopword Generation Based on Attention for Document Classification Using Neural Networks | |||||||||
| タイトル | ||||||||||
| 言語 | en | |||||||||
| タイトル | Automatic Stopword Generation Based on Attention for Document Classification Using Neural Networks | |||||||||
| 言語 | ||||||||||
| 言語 | eng | |||||||||
| キーワード | ||||||||||
| 主題Scheme | Other | |||||||||
| 主題 | [研究論文] stopwords, attention, BERT, neural network, text classification, machine learning, natural language processing | |||||||||
| 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 | |||||||||
| 著者所属 | ||||||||||
| Gifu University | ||||||||||
| 著者所属 | ||||||||||
| Gifu University | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| Gifu University | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| Gifu University | ||||||||||
| 著者名 |
Yuki, Kuwabara
× Yuki, Kuwabara
× Yu, Suzuki
|
|||||||||
| 著者名(英) |
Yuki, Kuwabara
× Yuki, Kuwabara
× Yu, Suzuki
|
|||||||||
| 論文抄録 | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | Stopwords are generally used to improve the accuracy of document classification and retrieval. We believe that setting appropriate stopwords improves classification accuracy. However, in our preliminary experiments, in document classification tasks using BERT, existing stopword lists are not effective for improving classification accuracy. To solve this problem, we construct a method for generating stopwords using the attention mechanism of the classifiers. In this method, words with high attention in misclassified input documents and low attention in correctly classified documents are treated as stopwords. The system probabilistically removes stopwords. The system automatically sets the probability of each word in input documents being a stopword when it builds the classification model. We conduct experiments to confirm effectiveness of our stopword generation method. Our experimental results show that there are cases using stopwords generated by our method that improve the classification accuracy. Three of the six classification tasks tested in this study show significant differences in accuracy improvement. ------------------------------ This is a preprint of an article intended for publication Journal of Information Processing(JIP). This preprint should not be cited. This article should be cited as: Journal of Information Processing Vol.32(2024) (online) ------------------------------ |
|||||||||
| 論文抄録(英) | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | Stopwords are generally used to improve the accuracy of document classification and retrieval. We believe that setting appropriate stopwords improves classification accuracy. However, in our preliminary experiments, in document classification tasks using BERT, existing stopword lists are not effective for improving classification accuracy. To solve this problem, we construct a method for generating stopwords using the attention mechanism of the classifiers. In this method, words with high attention in misclassified input documents and low attention in correctly classified documents are treated as stopwords. The system probabilistically removes stopwords. The system automatically sets the probability of each word in input documents being a stopword when it builds the classification model. We conduct experiments to confirm effectiveness of our stopword generation method. Our experimental results show that there are cases using stopwords generated by our method that improve the classification accuracy. Three of the six classification tasks tested in this study show significant differences in accuracy improvement. ------------------------------ This is a preprint of an article intended for publication Journal of Information Processing(JIP). This preprint should not be cited. This article should be cited as: Journal of Information Processing Vol.32(2024) (online) ------------------------------ |
|||||||||
| 書誌レコードID | ||||||||||
| 収録物識別子タイプ | NCID | |||||||||
| 収録物識別子 | AA11464847 | |||||||||
| 書誌情報 |
情報処理学会論文誌データベース（TOD） 巻 17, 号 2, 発行日 2024-04-23 |
|||||||||
| ISSN | ||||||||||
| 収録物識別子タイプ | ISSN | |||||||||
| 収録物識別子 | 1882-7799 | |||||||||
| 出版者 | ||||||||||
| 言語 | ja | |||||||||
| 出版者 | 情報処理学会 | |||||||||
