UKTA: Unified Korean Text Analyzer

TL;DR

UKTA is a comprehensive system for Korean text analysis and writing evaluation that improves accuracy, explainability, and multi-view analysis, addressing key challenges faced by existing tools.

Contribution

UKTA introduces a unified approach combining low-level morpheme analysis, lexical features, and transparent scoring for Korean writing evaluation.

Findings

Enhanced accuracy and quadratic weighted kappa over baselines

Provides multi-view analysis and explainability in Korean text evaluation

Positions as a leading multi-perspective Korean text analysis tool

Abstract

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.