Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization

TL;DR

This paper introduces an interpretable generative framework for creating mnemonic aids for kanji learning, using an EM algorithm to model the compositional structure and improve mnemonic generation interpretability.

Contribution

It presents a novel EM-based method that explicitly models mnemonic construction rules, enhancing interpretability and systematic generation of mnemonics for kanji learning.

Findings

Performs well in cold-start scenarios for new learners.

Provides insights into mnemonic creation mechanisms.

Learns latent structures from learner-authored mnemonics.

Abstract

Learning Japanese vocabulary is a challenge for learners from Roman alphabet backgrounds due to script differences. Japanese combines syllabaries like hiragana with kanji, which are logographic characters of Chinese origin. Kanji are also complicated due to their complexity and volume. Keyword mnemonics are a common strategy to aid memorization, often using the compositional structure of kanji to form vivid associations. Despite recent efforts to use large language models (LLMs) to assist learners, existing methods for LLM-based keyword mnemonic generation function as a black box, offering limited interpretability. We propose a generative framework that explicitly models the mnemonic construction process as driven by a set of common rules, and learn them using a novel Expectation-Maximization-type algorithm. Trained on learner-authored mnemonics from an online platform, our method learns latent structures and compositional rules, enabling interpretable and systematic mnemonics generation. Experiments show that our method performs well in the cold-start setting for new learners while providing insight into the mechanisms behind effective mnemonic creation.