mlsanityData to 14 Oct 2026

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

arXiv 2507.04018 ↗First posted 5 Jul 2025cs.CLcited by 0

Not on the map. Why?

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.

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

21 of 37 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  3. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  4. 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 546
  5. 2021KLUE: Korean Language Understanding Evaluationcited by 114
  6. 2017Deep Text Classification Can be Fooledcited by 106
  7. 2020Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERTcited by 69
  8. 2020An Empirical Study of Tokenization Strategies for Various Korean NLP Taskscited by 33
  9. 2017Mimicking Word Embeddings using Subword RNNscited by 30
  10. 2019Few-Shot Representation Learning for Out-Of-Vocabulary Wordscited by 30
  11. 2021Phoneme-BERT: Joint Language Modelling of Phoneme Sequence and ASR Transcriptcited by 21
  12. 2022Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularitycited by 19
9 more
  1. 2019Attentive Mimicking: Better Word Embeddings by Attending to Informative Contextscited by 17
  2. 2016Charagram: Embedding Words and Sentences via Character n-gramscited by 14
  3. 2022KOLD: Korean Offensive Language Datasetcited by 14
  4. 2023Disentangled Phonetic Representation for Chinese Spelling Correctioncited by 14
  5. 2023The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any languagecited by 14
  6. 2018Generalizing Word Embeddings using Bag of Subwordscited by 9
  7. 2022Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Costcited by 9
  8. 2018Learning Semantic Representations for Novel Words: Leveraging Both Form and Contextcited by 8
  9. 2019A Systematic Study of Leveraging Subword Information for Learning Word Representationscited by 6

Built on by

Not cited yet.