Saved in:
Bibliographic Details
Main Authors: Kang, Sana, Gwon, Myeongseok, Kwon, Su Young, Lee, Jaewook, Lan, Andrew, Raj, Bhiksha, Singh, Rita
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.05444
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909838976483328
author Kang, Sana
Gwon, Myeongseok
Kwon, Su Young
Lee, Jaewook
Lan, Andrew
Raj, Bhiksha
Singh, Rita
author_facet Kang, Sana
Gwon, Myeongseok
Kwon, Su Young
Lee, Jaewook
Lan, Andrew
Raj, Bhiksha
Singh, Rita
contents Vocabulary acquisition poses a significant challenge for second-language (L2) learners, especially when learning typologically distant languages such as English and Korean, where phonological and structural mismatches complicate vocabulary learning. Recently, large language models (LLMs) have been used to generate keyword mnemonics by leveraging similar keywords from a learner's first language (L1) to aid in acquiring L2 vocabulary. However, most methods still rely on direct IPA-based phonetic matching or employ LLMs without phonological guidance. In this paper, we present PhoniTale, a novel cross-lingual mnemonic generation system that performs IPA-based phonological adaptation and syllable-aware alignment to retrieve L1 keyword sequence and uses LLMs to generate verbal cues. We evaluate PhoniTale through automated metrics and a short-term recall test with human participants, comparing its output to human-written and prior automated mnemonics. Our findings show that PhoniTale consistently outperforms previous automated approaches and achieves quality comparable to human-written mnemonics.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05444
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PhoniTale: Phonologically Grounded Mnemonic Generation for Typologically Distant Language Pairs
Kang, Sana
Gwon, Myeongseok
Kwon, Su Young
Lee, Jaewook
Lan, Andrew
Raj, Bhiksha
Singh, Rita
Computation and Language
Vocabulary acquisition poses a significant challenge for second-language (L2) learners, especially when learning typologically distant languages such as English and Korean, where phonological and structural mismatches complicate vocabulary learning. Recently, large language models (LLMs) have been used to generate keyword mnemonics by leveraging similar keywords from a learner's first language (L1) to aid in acquiring L2 vocabulary. However, most methods still rely on direct IPA-based phonetic matching or employ LLMs without phonological guidance. In this paper, we present PhoniTale, a novel cross-lingual mnemonic generation system that performs IPA-based phonological adaptation and syllable-aware alignment to retrieve L1 keyword sequence and uses LLMs to generate verbal cues. We evaluate PhoniTale through automated metrics and a short-term recall test with human participants, comparing its output to human-written and prior automated mnemonics. Our findings show that PhoniTale consistently outperforms previous automated approaches and achieves quality comparable to human-written mnemonics.
title PhoniTale: Phonologically Grounded Mnemonic Generation for Typologically Distant Language Pairs
topic Computation and Language
url https://arxiv.org/abs/2507.05444