The Todai Robot Project: Error Analysis on the Results of the Yozemi Center Test

• Matsuzaki Takuya

  Graduate School of Engineering, Nagoya University

• Yokono Hikaru

  National Institute of Informatics

• Miyao Yusuke

  National Institute of Informatics

• Kawazoe Ai

  National Institute of Informatics

• Kano Yoshinobu

  Faculty of Informatics, Shizuoka University

• Kanou Hayato

  Graduate School of Engineering, Nagoya University

• Sato Satoshi

  Graduate School of Engineering, Nagoya University

• Higashinaka Ryuichiro

  NTT Communication Science Laboratories, NTT Corporation

• Sugiyama Hiroaki

  NTT Communication Science Laboratories, NTT Corporation

• Isozaki Hideki

  Faculty of Computer Science and Systems Engineering, Okayama Prefectural University

• Kikui Genichiro

  Faculty of Computer Science and Systems Engineering, Okayama Prefectural University

• Dosaka Koji

  Faculty of Systems Science and Technology, Akita Prefectural University

• Taira Hirotoshi

  Faculty of Information Science and Technology, Osaka Institute of Technology

• Minami Yasuhiro

  Graduate School of Information Systems, The University of Electoro-Comunications

• H. Arai Noriko

  National Institute of Informatics

Bibliographic Information

Other Title

• 「ロボットは東大に入れるか」プロジェクト： 代ゼミセンター模試タスクにおけるエラーの分析
• 「 ロボット ワ トウダイ ニ イレル カ 」 プロジェクト : ダイ ゼミセンター モシ タスク ニ オケル エラー ノ ブンセキ

Abstract

The Todai Robot Project aims at integrating various AI technologies including natural language processing (NLP), as well as uncovering novel AI problems that have been missed while the fragmentation of the research field, through the development of software systems that solve university entrance exam problems. Being primarily designed for the measurement of human intellectual abilities, university entrance exam problems serve as an ideal benchmark for AI technologies. They also enable a quantitative comparison between the AI systems and human test takers. This paper analyzes the errors made by the software systems on the mock university entrance exams hosted by a popular preparatory school. Based on the analyses, key problems towards higher system performances and the current issues in the field of NLP are discussed.

Journal

• Journal of Natural Language Processing

  Journal of Natural Language Processing 23 (1), 119-159, 2016

  The Association for Natural Language Processing

Keywords

• Integrated AI Tasks
• University Entrance Examinations
• Error Analysis

Details

• CRID: 1390001204475379328
• NII Article ID: 130005147080
• NII Book ID: AN10472659
• DOI: 10.5715/jnlp.23.119
• ISSN: 21858314
• ISSN: 13407619
• NDL BIB ID: 027091053
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I027091053
• Web Site: https://www.jstage.jst.go.jp/article/jnlp/23/1/23_119/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed