Papers by Youjeong Roh
Happiness is Sharing a Vocabulary: A Study of Transliteration Methods (2026.eacl-long)
Copied to clipboard
| Challenge: | a key problem in multilingual NLP is script barrier, which makes it difficult to share knowledge between languages . a new study shows that transliteration can be useful for languages using non-Latin scripts . |
| Approach: | They propose to use romanization, phonemic transcription, and substitution ciphers to evaluate models . romanization outperforms other input types in 7 out of 8 evaluation settings . |
| Outcome: | The proposed approach outperforms other input types on three tasks and is the most effective . romanization outperformed other input type in 7 out of 8 evaluation settings . |
gMBA: Expression Semantic Guided Mixed Boolean-Arithmetic Deobfuscation Using Transformer Architectures (2025.findings-acl)
Copied to clipboard
| Challenge: | Mixed Boolean-Arithmetic (MBA) obfuscation protects intellectual property by converting programs into complex forms that are difficult to analyze. |
| Approach: | They propose a mixed-boolean-arithmetic (MBA) obfuscation framework that transforms a Transformer-based neural encoder-decoder into a truth table that is an automatically constructed semantic representation of an expression's behavior. |
| Outcome: | The proposed framework improves performance and highlights the importance of internal semantic expressions in recovering obfuscated code to its original form. |