Abstract
Automatically mapping written Kazakh to dictionary-linked Kazakh Sign Language (KSL) lexical signs is difficult because inflected forms often do not match canonical entries in limited digital lexicons. Surdo Med combines Kazakh natural-language processing, Dimskis notation, reusable avatar animation components, and a web interface for medical-domain lexical learning. This study evaluates morphology-aware lexical concept recovery rather than complete Kazakh-to-KSL translation. The primary benchmark uses naturally occurring inflected tokens from the official UD Kazakh-KTB test split that map uniquely to a frozen medical concept inventory. Across 373 supported inflected tokens, direct lookup recovered 1.61% of target concepts, a rule-based baseline recovered 45.31%, and contextual Stanza lemmatization recovered 97.86% (sentence-cluster bootstrap 95% CI: 96.29–99.19%). Recovery remained 96.85% after deduplicating surface–lemma pairs and 94.80% when macro-averaged across 52 lexical concepts. An external analysis using published KSL lexical material showed 20.0% overlap with the medical inventory; within supported items, Stanza recovered 6/6 root tokens versus 3/6 for direct lookup. These results support morphology-aware normalization for dictionary-linked KSL concept recovery. Avatar linguistic quality and educational effectiveness require separate human evaluation.