Ju-Hyoung Lee — accepted AI-conference papers

2024

SuperST: Superficial Self-Training for Few-Shot Text Classification

Ju-Hyoung Lee, Joonghyuk Hahn, Hyeon-Tae Seo, Jiho Park, Yo-Sub Han

COLING 2024main

In few-shot text classification, self-training is a popular tool in semi-supervised learning (SSL). It relies on pseudo-labels to expand data, which has demonstrated success. However, these pseudo-labels contain potential noise and provoke a risk of underfitting the decision boundary. While the pseu…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2021

SALNet: Semi-supervised Few-Shot Text Classification with Attention-based Lexicon Construction

Ju-Hyoung Lee, Sang-Ki Ko, Yo-Sub Han

AAAI 2021technical

We propose a semi-supervised bootstrap learning framework for few-shot text classification. From a small amount of the initial dataset, our framework obtains a larger set of reliable training data by using the attention weights from an LSTM-based trained classifier. We first train an LSTM-based text…

Cited by 26 Source ↗PDF ↗Scholar ↗