HongSeok Choi


pdf bib
Early Stopping Based on Unlabeled Samples in Text Classification
HongSeok Choi | Dongha Choi | Hyunju Lee
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Early stopping, which is widely used to prevent overfitting, is generally based on a separate validation set. However, in low resource settings, validation-based stopping can be risky because a small validation set may not be sufficiently representative, and the reduction in the number of samples by validation split may result in insufficient samples for training. In this study, we propose an early stopping method that uses unlabeled samples. The proposed method is based on confidence and class distribution similarities. To further improve the performance, we present a calibration method to better estimate the class distribution of the unlabeled samples. The proposed method is advantageous because it does not require a separate validation set and provides a better stopping point by using a large unlabeled set. Extensive experiments are conducted on five text classification datasets and several stop-methods are compared. Our results show that the proposed model even performs better than using an additional validation set as well as the existing stop-methods, in both balanced and imbalanced data settings. Our code is available at https://github.com/DMCB-GIST/BUS-stop.

pdf bib
Domain Knowledge Transferring for Pre-trained Language Model via Calibrated Activation Boundary Distillation
Dongha Choi | HongSeok Choi | Hyunju Lee
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Since the development and wide use of pretrained language models (PLMs), several approaches have been applied to boost their performance on downstream tasks in specific domains, such as biomedical or scientific domains. Additional pre-training with in-domain texts is the most common approach for providing domain-specific knowledge to PLMs. However, these pre-training methods require considerable in-domain data and training resources and a longer training time. Moreover, the training must be re-performed whenever a new PLM emerges. In this study, we propose a domain knowledge transferring (DoKTra) framework for PLMs without additional in-domain pretraining. Specifically, we extract the domain knowledge from an existing in-domain pretrained language model and transfer it to other PLMs by applying knowledge distillation. In particular, we employ activation boundary distillation, which focuses on the activation of hidden neurons. We also apply an entropy regularization term in both teacher training and distillation to encourage the model to generate reliable output probabilities, and thus aid the distillation. By applying the proposed DoKTra framework to downstream tasks in the biomedical, clinical, and financial domains, our student models can retain a high percentage of teacher performance and even outperform the teachers in certain tasks. Our code is available at https://github.com/DMCB-GIST/DoKTra.


pdf bib
GIST at SemEval-2018 Task 12: A network transferring inference knowledge to Argument Reasoning Comprehension task
HongSeok Choi | Hyunju Lee
Proceedings of the 12th International Workshop on Semantic Evaluation

This paper describes our GIST team system that participated in SemEval-2018 Argument Reasoning Comprehension task (Task 12). Here, we address two challenging factors: unstated common senses and two lexically close warrants that lead to contradicting claims. A key idea for our system is full use of transfer learning from the Natural Language Inference (NLI) task to this task. We used Enhanced Sequential Inference Model (ESIM) to learn the NLI dataset. We describe how to use ESIM for transfer learning to choose correct warrant through a proposed system. We show comparable results through ablation experiments. Our system ranked 1st among 22 systems, outperforming all the systems more than 10%.