activity
20172025
most citedReducing the Cost: Cross-Prompt Pre-Finetuning for Short Answer Scoring

13 citations · 21 across the 6 of their papers we have counts for

collaborators

9 papers

cs.CL2025

Tell Me Who Your Students Are: GPT Can Generate Valid Multiple-Choice Questions When Students' (Mis)Understanding Is Hinted

Machi Shimmei, Masaki Uto, Yuichiroh Matsubayashi +3

The primary goal of this study is to develop and evaluate an innovative prompting technique, AnaQuest, for generating multiple-choice questions (MCQs) using a pre-trained large lan…

cs.CL2025

Automatic Feedback Generation for Short Answer Questions using Answer Diagnostic Graphs

Momoka Furuhashi, Hiroaki Funayama, Yuya Iwase +5

Short-reading comprehension questions help students understand text structure but lack effective feedback. Students struggle to identify and correct errors, while manual feedback c…

cs.CL202413 cited

Reducing the Cost: Cross-Prompt Pre-Finetuning for Short Answer Scoring

Hiroaki Funayama, Yuya Asazuma, Yuichiroh Matsubayashi +2

Automated Short Answer Scoring (SAS) is the task of automatically scoring a given input to a prompt based on rubrics and reference answers. Although SAS is useful in real-world app…

cs.CL2024

To Drop or Not to Drop? Predicting Argument Ellipsis Judgments: A Case Study in Japanese

Yukiko Ishizuki, Tatsuki Kuribayashi, Yuichiroh Matsubayashi +2

Speakers sometimes omit certain arguments of a predicate in a sentence; such omission is especially frequent in pro-drop languages. This study addresses a question about ellipsis -…

cs.CL2024

Japanese-English Sentence Translation Exercises Dataset for Automatic Grading

Naoki Miura, Hiroaki Funayama, Seiya Kikuchi +3

This paper proposes the task of automatic assessment of Sentence Translation Exercises (STEs), that have been used in the early stage of L2 language learning. We formalize the task…

cs.CL2021

Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution

Ryuto Konno, Shun Kiyono, Yuichiroh Matsubayashi +2

Masked language models (MLMs) have contributed to drastic performance improvements with regard to zero anaphora resolution (ZAR). To further improve this approach, in this study, w…