Papers by Jong-Hyeok Lee
Decay-Function-Free Time-Aware Attention to Context and Speaker Indicator for Spoken Language Understanding (N19-1)
Copied to clipboard
| Challenge: | Existing models that use contextual information of dialogues to improve spoken language understanding (SLU) select the wrong history when the histories are similar in content. |
| Approach: | They propose time-aware models that automatically learn the latent time-decay function of the history without a manual time- decay. |
| Outcome: | The proposed models achieve higher F1 scores than state-of-the-art models on a benchmark dataset . |
Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations (2023.acl-short)
Copied to clipboard
| Challenge: | Existing APE systems are not good at handling high-quality MTs even for a language pair with abundant data resources, English–German. |
| Approach: | They propose a linguistically motivated method of regularization that encourages symmetric self-attention on the given MT. |
| Outcome: | The proposed method improves the state-of-the-art architecture’s APE quality for high-quality MTs. |
Advancing Semi-Supervised Learning for Automatic Post-Editing: Data-Synthesis by Mask-Infilling with Erroneous Terms (2024.lrec-main)
Copied to clipboard
| Challenge: | Semi-supervised learning that leverages synthetic data for training has been widely adopted for developing automatic post-editing models due to the lack of training data. |
| Approach: | They propose a method that uses masked tokens to generate a noisy text from a clean text by infilling mangled tokens with erroneous tokens. |
| Outcome: | The proposed method mimics translation errors found in real data and generates a noisy text from a clean text by infilling masked tokens with erroneous tokens. |
Adaptation of Back-translation to Automatic Post-Editing for Synthetic Data Generation (2021.eacl-main)
Copied to clipboard
| Challenge: | Automated Post-Editing (APE) aims to correct errors in the output of a given machine translation system. |
| Approach: | They propose two new methods of synthesizing additional MT outputs by adapting back-translation to the APE task, obtaining robust enlargements of existing synthetic APE training dataset. |
| Outcome: | The proposed methods improve translation quality on the English-German APE task by enlarging the existing training dataset. |