Guardado en:
Detalles Bibliográficos
Autores principales: Ahn, Seokho, Park, Junhyung, Go, Ganghee, Kim, Chulhui, Jung, Jiho, Shin, Myung Sun, Kim, Do-Guk, Seo, Young-Duk
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2502.09648
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909493047066624
author Ahn, Seokho
Park, Junhyung
Go, Ganghee
Kim, Chulhui
Jung, Jiho
Shin, Myung Sun
Kim, Do-Guk
Seo, Young-Duk
author_facet Ahn, Seokho
Park, Junhyung
Go, Ganghee
Kim, Chulhui
Jung, Jiho
Shin, Myung Sun
Kim, Do-Guk
Seo, Young-Duk
contents Evaluating writing quality is complex and time-consuming often delaying feedback to learners. While automated writing evaluation tools are effective for English, Korean automated writing evaluation tools face challenges due to their inability to address multi-view analysis, error propagation, and evaluation explainability. To overcome these challenges, we introduce UKTA (Unified Korean Text Analyzer), a comprehensive Korea text analysis and writing evaluation system. UKTA provides accurate low-level morpheme analysis, key lexical features for mid-level explainability, and transparent high-level rubric-based writing scores. Our approach enhances accuracy and quadratic weighted kappa over existing baseline, positioning UKTA as a leading multi-perspective tool for Korean text analysis and writing evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2502_09648
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UKTA: Unified Korean Text Analyzer
Ahn, Seokho
Park, Junhyung
Go, Ganghee
Kim, Chulhui
Jung, Jiho
Shin, Myung Sun
Kim, Do-Guk
Seo, Young-Duk
Computation and Language
Artificial Intelligence
Evaluating writing quality is complex and time-consuming often delaying feedback to learners. While automated writing evaluation tools are effective for English, Korean automated writing evaluation tools face challenges due to their inability to address multi-view analysis, error propagation, and evaluation explainability. To overcome these challenges, we introduce UKTA (Unified Korean Text Analyzer), a comprehensive Korea text analysis and writing evaluation system. UKTA provides accurate low-level morpheme analysis, key lexical features for mid-level explainability, and transparent high-level rubric-based writing scores. Our approach enhances accuracy and quadratic weighted kappa over existing baseline, positioning UKTA as a leading multi-perspective tool for Korean text analysis and writing evaluation.
title UKTA: Unified Korean Text Analyzer
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2502.09648