| 講演抄録/キーワード |
| 講演名 |
2012-08-31 15:10
手掛語による論文概要中の問題文の特徴付け ○酒井敏彦・廣川佐千男(九大) NLC2012-23 |
| 抄録 |
(和) |
関連研究について文献調査を行うとき,単純なキーワード検索だと,検索結果を詳細に読まなければ,各論文の問題や手法は理解できない.これらの観点での検索ができれば,調査の効率向上が期待できる.本稿では,論文概要の中で問題を表す文(問題文)を特徴づける手掛語をSVMで求める.通常の10分割交差検定では,手掛語集合を限定するより,全ての単語を使った方が判別性能は高い.ところが,学習サンプル数が少ない場合,全ての単語を使うより,手掛語集合を限定した方が問題文判別性能が高くなり,手掛語の有効性を確認できた. |
| (英) |
The literature survey on related work requires a lot of efforts in reading all articles that are retrieved by queries. We have to understand the contents from several view points, such as the problem and the method that the articles describe. Search from these viewpoints will improve the efficiency of survey, if particular segments of articles were extracted, indexed and can be used as auxiliary query.
This paper focuses on the sentence that describes the problem in an abstract and the feature sets that describe such problem sentences. Discernment performance are evaluated by 10-fold cross-validation for six candidates of feature word sets. It turned out that the set of all words gains the best performance if 90% of the data are used as training data. However, the set of a small number of words with positive scores outperforms other feature sets, if the training data is only 10%. In such a realistic situation, the feature words are effective in improving discernment. |
| キーワード |
(和) |
手掛語 / SVM / 交差検定 / 学術論文 / / / / |
| (英) |
Feature Words / SVM / Cross validation / Scientific Article / / / / |
| 文献情報 |
信学技報, vol. 112, no. 196, NLC2012-23, pp. 73-78, 2012年8月. |
| 資料番号 |
NLC2012-23 |
| 発行日 |
2012-08-23 (NLC) |
| ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
| PDFダウンロード |
NLC2012-23 |