Saved in:
| Main Authors: | , , , , , , |
|---|---|
| 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 |