Improving the robustness and accuracy of biomedical language models through adversarial training
Deep transformer neural network models have improved the predictive accuracy of intelligent text processing systems in the biomedical domain. They have obtained state-of-the-art performance scores on a wide variety of biomedical and clinical Natural Language Processing (NLP) benchmarks. However, the...
Main Authors: | Moradi, M. (Author), Samwald, M. (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
Academic Press Inc.
2022
|
Subjects: | |
Online Access: | View Fulltext in Publisher |
Similar Items
-
Generating Semantically Similar and Human-Readable Summaries With Generative Adversarial Networks
by: Haojie Zhuang, et al.
Published: (2019-01-01) -
A2R2: Robust Unsupervised Neural Machine Translation With Adversarial Attack and Regularization on Representations
by: Heng Yu, et al.
Published: (2021-01-01) -
Corpus construction based on Ontological domain knowledge
by: Benis, Nirupama, et al.
Published: (2011) -
Detection of Loanwords in Angolan Portuguese: A Text Mining Approach
by: Brazdil, P.B, et al.
Published: (2022) -
On the crucial role of multilingual biomedical databases in epidemic events (SARS-CoV-2 analysis)
by: Felipe Soares, et al.
Published: (2020-07-01)