Reading Skill Test to Diagnose Basic Language Skills in Comparison to Machines
- Noriko Arai, National Institute of Informatics, Chiyoda-ku, Tokyo, Japan
- Naoya Todo, NIAD-QE, Kodaira, Tokyo, Japan
- Teiko Arai, University of Tokyo, Bunkyo-ku, Tokyo, Japan
- Kyosuke Bunji, University of Tokyo, Bunkyo-ku, Tokyo, Japan
- Shingo Sugawara, Hosei University, Chiyoda-ku, Tokyo, Japan
- Miwa Inuzuka, Taisho University, Toshimaku, Tokyo, Japan
- Takuya Matsuzaki, Nagoya University, Nagoya, Aichi, Japan
- Koken Ozaki, University of Tsukuba, Bunkyo-ku, Tokyo, Japan
Abstract
A reading skill test to diagnose basic language skills is
introduced. The test is designed to measure six component skills relevant to
reading in comparison with those of state-of-the-art natural language processing
technologies. The results of the first large-scale experiments using the test are
reported. Surprisingly, almost half of Japanese junior high school students do no
better than machines in dependency analysis. More than half of 7th grade students
do no better than making random choices on questions involving inferences and
definition understanding.
Back to Table of Contents