# Handling Korean Out-of-Vocabulary Words with Phoneme Representation Learning

arXiv: https://arxiv.org/abs/2507.04018 · HTML: https://mlsanity.com/paper/2507.04018/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 5 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [KLUE: Korean Language Understanding Evaluation](https://mlsanity.com/paper/2105.09680/) (2021)
- [Deep Text Classification Can be Fooled](https://mlsanity.com/paper/1704.08006/) (2017)
- [Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT](https://mlsanity.com/paper/2003.04985/) (2020)
- [An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks](https://mlsanity.com/paper/2010.02534/) (2020)
- [Mimicking Word Embeddings using Subword RNNs](https://mlsanity.com/paper/1707.06961/) (2017)
- [Few-Shot Representation Learning for Out-Of-Vocabulary Words](https://mlsanity.com/paper/1907.00505/) (2019)
- [Phoneme-BERT: Joint Language Modelling of Phoneme Sequence and ASR Transcript](https://mlsanity.com/paper/2102.00804/) (2021)
- [Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity](https://mlsanity.com/paper/2210.10996/) (2022)
- [Attentive Mimicking: Better Word Embeddings by Attending to Informative Contexts](https://mlsanity.com/paper/1904.01617/) (2019)
- [Charagram: Embedding Words and Sentences via Character n-grams](https://mlsanity.com/paper/1607.02789/) (2016)
- [KOLD: Korean Offensive Language Dataset](https://mlsanity.com/paper/2205.11315/) (2022)
- [Disentangled Phonetic Representation for Chinese Spelling Correction](https://mlsanity.com/paper/2305.14783/) (2023)
- [The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any language](https://mlsanity.com/paper/2311.08323/) (2023)
- [Generalizing Word Embeddings using Bag of Subwords](https://mlsanity.com/paper/1809.04259/) (2018)
- [Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost](https://mlsanity.com/paper/2203.07860/) (2022)
- [Learning Semantic Representations for Novel Words: Leveraging Both Form and Context](https://mlsanity.com/paper/1811.03866/) (2018)
- [A Systematic Study of Leveraging Subword Information for Learning Word Representations](https://mlsanity.com/paper/1904.07994/) (2019)

## Abstract (arXiv)

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.