Handling Korean Out-of-Vocabulary Words with Phoneme Representation Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909676807913472 |
|---|---|
| author | Kim, Nayeon Jeon, Eojin Park, Jun-Hyung Lee, SangKeun |
| author_facet | Kim, Nayeon Jeon, Eojin Park, Jun-Hyung Lee, SangKeun |
| contents | In this study, we introduce KOPL, a novel framework for handling Korean OOV words with Phoneme representation Learning. Our work is based on the linguistic property of Korean as a phonemic script, the high correlation between phonemes and letters. KOPL incorporates phoneme and word representations for Korean OOV words, facilitating Korean OOV word representations to capture both text and phoneme information of words. We empirically demonstrate that KOPL significantly improves the performance on Korean Natural Language Processing (NLP) tasks, while being readily integrated into existing static and contextual Korean embedding models in a plug-and-play manner. Notably, we show that KOPL outperforms the state-of-the-art model by an average of 1.9%. Our code is available at https://github.com/jej127/KOPL.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04018 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Handling Korean Out-of-Vocabulary Words with Phoneme Representation Learning Kim, Nayeon Jeon, Eojin Park, Jun-Hyung Lee, SangKeun Computation and Language In this study, we introduce KOPL, a novel framework for handling Korean OOV words with Phoneme representation Learning. Our work is based on the linguistic property of Korean as a phonemic script, the high correlation between phonemes and letters. KOPL incorporates phoneme and word representations for Korean OOV words, facilitating Korean OOV word representations to capture both text and phoneme information of words. We empirically demonstrate that KOPL significantly improves the performance on Korean Natural Language Processing (NLP) tasks, while being readily integrated into existing static and contextual Korean embedding models in a plug-and-play manner. Notably, we show that KOPL outperforms the state-of-the-art model by an average of 1.9%. Our code is available at https://github.com/jej127/KOPL.git. |
| title | Handling Korean Out-of-Vocabulary Words with Phoneme Representation Learning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.04018 |