| ID | 56445 |
| Title Alternative | A Study of Extracting Related Documents for Essay Evaluation Modules
|
| FullText URL | |
| Author |
Motojin, Kota
Graduate School of Natural Science and Technology, Okayama University
Takeuchi, Koichi
Graduate School of Natural Science and Technology, Okayama University
Kaken ID
publons
researchmap
Ohno, Masayuki
Graduate School of Natural Science and Technology, Okayama University
Taguchi, Masahiro
Graduate School of Natural Science and Technology, Okayama University
Kaken ID
publons
researchmap
Inada, Yoshihiko
Graduate School of Natural Science and Technology, Okayama University
ORCID
Kaken ID
publons
researchmap
Iizuka, Masaya
Graduate School of Natural Science and Technology, Okayama University
Kaken ID
researchmap
Abo, Tatsuhiko
Graduate School of Natural Science and Technology, Okayama University
Ueda, Hitoshi
Graduate School of Natural Science and Technology, Okayama University
|
| Abstract | 本研究では，小論文採点システムにおいて必要となる小論文に関連した文書を取得する方法を開発した．本研究プロジェクトの自動採点の評価軸の1 つに「妥当性」がある．妥当性の評価手法として，小論文の内容がWikipediaの文書の内容と，どの程度一致しているかを基準に妥当性スコアを算出する方法を考えている．しかし，Wikipediaの文書は多様であり，小論文で取り上げていない議題に関する文書も多く存在する．そこで本論文では小論文ごとに適切な文書を取得する方法を提案する．いくつかの手法を試した結果，単語ベクトルを使用した方法が，関連した文書を獲得することができたことを報告する．
|
| 抄録（別言語） | We are developing an automatic Japanese essay-scoring system that is composed of 4 evaluation criteria, comprehensiveness, logical consistency, validity, spelling and grammar. In this paper, we discuss the most powerful approach to extract documents of Wikipedia that relates to the reference texts of the target essay theme for validity evaluation. The reason for using Wikipedia documents for evaluating validity of students’essays is that we assume that validity can be evaluated by the expanded discussions in Wikipedia documents that relates to the essay theme. Experimental results show that the skip-gram based word vector is the best approach to extract relating documents to reference texts among several keyword-based evaluation approaches.
|
| Keywords | 小論文の自動採点 (Automatic scoring of answers of essay-writing tests)
単語ベクトル (Word vector)
Skip-gram
Wikipedia
|
| Published Date | 2017-09
|
| Publication Title |
IEICE technical report. Natural language processing and models of communication
|
| Volume | volume117
|
| Issue | issue207
|
| Publisher | 電子情報通信学会
|
| Start Page | 47
|
| End Page | 51
|
| ISSN | 09135685
|
| NCID | AA11524632
|
| Content Type |
Journal Article
|
| language |
Japanese
|
| OAI-PMH Set |
岡山大学
|
| Copyright Holders | copyright©2017 IEICE
|
| File Version | publisher
|
