Abstract
This laboratory-based user study is designed to evaluate automated mnemonic keywords generation systems for Japanese vocabulary learning. We examine our successful methodology and in particular a new phonetic algorithm, named JemSoundex, for Japanese-to-English-Mnemonic phonetic matching, in a learning and immediate retention task. Our methodology retrieves and ranks candidate keywords by considering phonetic, orthographic and semantic similarities, as well as psycholinguistic power. Experimental results showed that keywords provided by JemSoundex improved learner performance in the task of a short-term vocabulary learning, in comparison with no keyword support and two traditional phonetic transcriptions (i.e., IPA and Soundex). This improvement was even more evident for difficult words having more syllables. Participants also rated keywords generated by our JemSoundex as more phonetically relevant and useful than those by other baselines.