Extracting Chemical-Protein Interactions via Calibrated Deep Neural Network and Self-training

Dongha Choi, Hyunju Lee


Abstract
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.
Anthology ID:
2020.findings-emnlp.189
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2086–2095
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.189
DOI:
10.18653/v1/2020.findings-emnlp.189
Bibkey:
Cite (ACL):
Dongha Choi and Hyunju Lee. 2020. Extracting Chemical-Protein Interactions via Calibrated Deep Neural Network and Self-training. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2086–2095, Online. Association for Computational Linguistics.
Cite (Informal):
Extracting Chemical-Protein Interactions via Calibrated Deep Neural Network and Self-training (Choi & Lee, Findings 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2020.findings-emnlp.189.pdf
Optional supplementary material:
 2020.findings-emnlp.189.OptionalSupplementaryMaterial.zip