Automatic Feedback Generation for Japanese Reading Comprehension Short-Answer Questions Using Discourse-Structure-based Answer Diagnostic Graphs
Journal of Natural Language Processing · 2026 · 33 (1) · 240-282
DOI: 10.5715/jnlp.33.240 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Natural Language Processing, 2026. Verfasst von Momoka Furuhashi und 6 weiteren Autor:innen. Die Arbeit nennt 65 Literaturangaben.
Abstract (Originalsprache)
Short-Answer Reading Comprehension (SARC) questions are widely used in reading education. However, providing feedback on student responses requires substantial time and effort due to the wide variety of incorrect responses. To address this, we propose an automatic feedback-generation method for questions that require an understanding of the logical structure of a given prompt text. We introduce an Answer Diagnostic Graph (ADG) that represents the text's logical structure as a graph: nodes are textual elements and edges represent logical relationships. Feedback templates are linked to edges to explain how the parts of the prompt text are logically connected. To generate feedback, we formulated a classification task that identifies the reference node, from the part of the text that the student is likely to refer to based on the ADG. The experiments included technical and human evaluations by four experts. Technical evaluation showed high accuracy of reference-node prediction for most questions, suggesting that it influenced human judgment. Human evaluations compared feedback from our method and large language model (LLM) across four criteria: reference indication, logical structure, difference from model answers, and overall satisfaction. Our proposed method outperformed the LLM on all criteria, with statistically significant differences (p < .001) for three of the four evaluators, demonstrating the effectiveness of the approach.
Zitieren
APA
Furuhashi, M., Funayama, H., Matsubayashi, Y., Shimmei, M., Isobe, Y., Ishii, Y., & Inui, K. (2026). Automatic Feedback Generation for Japanese Reading Comprehension Short-Answer Questions Using Discourse-Structure-based Answer Diagnostic Graphs. Journal of Natural Language Processing, 33(1), 240-282. https://doi.org/10.5715/jnlp.33.240
Vancouver
Furuhashi M, Funayama H, Matsubayashi Y, Shimmei M, Isobe Y, Ishii Y, et al. Automatic Feedback Generation for Japanese Reading Comprehension Short-Answer Questions Using Discourse-Structure-based Answer Diagnostic Graphs. Journal of Natural Language Processing. 2026;33(1):240-282. doi:10.5715/jnlp.33.240
BibTeX
@article{Furuhashi2026,
author = {Furuhashi, Momoka and Funayama, Hiroaki and Matsubayashi, Yuichiroh and Shimmei, Machi and Isobe, Yoriko and Ishii, Yutaka and Inui, Kentaro},
title = {Automatic Feedback Generation for Japanese Reading Comprehension Short-Answer Questions Using Discourse-Structure-based Answer Diagnostic Graphs},
journal = {Journal of Natural Language Processing},
year = {2026},
volume = {33},
number = {1},
pages = {240--282},
doi = {10.5715/jnlp.33.240}
}
EUVIMED