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.

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.

The extraction of interactions between chemicals and proteins from several biomedical articles is important in many fields of biomedical research such as drug development and prediction of drug side effects. Several natural language processing methods, including deep neural network (DNN) models, have been applied to address this problem. However, these methods were trained with hard-labeled data, which tend to become over-confident, leading to degradation of the model reliability. To estimate the data uncertainty and improve the reliability, “calibration” techniques have been applied to deep learning models. In this study, to extract chemical–protein interactions, we propose a DNN-based approach incorporating uncertainty information and calibration techniques. Our model first encodes the input sequence using a pre-trained language-understanding model, following which it is trained using two calibration methods: mixup training and addition of a confidence penalty loss. Finally, the model is re-trained with augmented data that are extracted using the estimated uncertainties. Our approach has achieved state-of-the-art performance with regard to the Biocreative VI ChemProt task, while preserving higher calibration abilities than those of previous approaches. Furthermore, our approach also presents the possibilities of using uncertainty estimation for performance improvement.

This paper describes a system attended in the SemEval-2018 Task 1 “Affect in tweets” that predicts emotional intensities. We use Group LSTM with an attention model and transfer learning with sentiment classification data as a source data (SemEval 2017 Task 4a). A transfer model structure consists of a source domain and a target domain. Additionally, we try a new dropout that is applied to LSTMs in the Group LSTM. Our system ranked 8th at the subtask 1a (emotion intensity regression). We also show various results with different architectures in the source, target and transfer models.

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%.