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 robustness and reliability of these models has been less explored so far. Neural NLP models can be easily fooled by adversarial samples, i.e. minor changes to input that preserve the meaning and understandability of the text but force the NLP system to make erroneous decisions. This raises serious concerns about the security and trust-worthiness of biomedical NLP systems, especially when they are intended to be deployed in real-world use cases. We investigated the robustness of several transformer neural language models, i.e. BioBERT, SciBERT, BioMed-RoBERTa, and Bio-ClinicalBERT, on a wide range of biomedical and clinical text processing tasks. We implemented various adversarial attack methods to test the NLP systems in different attack scenarios. Experimental results showed that the biomedical NLP models are sensitive to adversarial samples; their performance dropped in average by 21 and 18.9 absolute percent on character-level and word-level adversarial noise, respectively, on Micro-F1, Pearson Correlation, and Accuracy measures. Conducting extensive adversarial training experiments, we fine-tuned the NLP models on a mixture of clean samples and adversarial inputs. Results showed that adversarial training is an effective defense mechanism against adversarial noise; the models' robustness improved in average by 11.3 absolute percent. In addition, the models' performance on clean data increased in average by 2.4 absolute percent, demonstrating that adversarial training can boost generalization abilities of biomedical NLP systems. This study takes an important step towards revealing vulnerabilities of deep neural language models in biomedical NLP applications. It also provides practical and effective strategies to develop secure, trust-worthy, and accurate intelligent text processing systems in the biomedical domain.

High-performance neural language models have obtained state-of-the-art results on a wide range of Natural Language Processing (NLP) tasks.However, results for common benchmark datasets often do not reflect model reliability and robustness when applied to noisy, real-world data.In this study, we design and implement various types of character-level and wordlevel perturbation methods to simulate realistic scenarios in which input texts may be slightly noisy or different from the data distribution on which NLP systems were trained.Conducting comprehensive experiments on different NLP tasks, we investigate the ability of high-performance language models such as BERT, XLNet, RoBERTa, and ELMo in handling different types of input perturbations.The results suggest that language models are sensitive to input perturbations and their performance can decrease even when small changes are introduced.We highlight that models need to be further improved and that current benchmarks are not reflecting model robustness well.We argue that evaluations on perturbed inputs should routinely complement widely-used benchmarks in order to yield a more realistic understanding of NLP systems' robustness.

Black-box Artificial Intelligence (AI) methods, e.g. deep neural networks, have been widely utilized to build predictive models that can extract complex relationships in a dataset and make predictions for new unseen data records. However, it is difficult to trust decisions made by such methods since their inner working and decision logic is hidden from the user. Explainable Artificial Intelligence (XAI) refers to systems that try to explain how a black-box AI model produces its outcomes. Post-hoc XAI methods approximate the behavior of a black-box by extracting relationships between feature values and the predictions. Perturbation-based and decision set methods are among commonly used post-hoc XAI systems. The former explanators rely on random perturbations of data records to build local or global linear models that explain individual predictions or the whole model. The latter explanators use those feature values that appear more frequently to construct a set of decision rules that produces the same outcomes as the target black-box. However, these two classes of XAI methods have some limitations. Random perturbations do not take into account the distribution of feature values in different subspaces, leading to misleading approximations. Decision sets only pay attention to frequent feature values and miss many important correlations between features and class labels that appear less frequently but accurately represent decision boundaries of the model. In this paper, we address the above challenges by proposing an explanation method named Confident Itemsets Explanation (CIE). We introduce confident itemsets, a set of feature values that are highly correlated to a specific class label. CIE utilizes confident itemsets to discretize the whole decision space of a model to smaller subspaces. Extracting important correlations between the features and the outcomes of the classifier in different subspaces, CIE produces instance-wise and class-wise explanations that accurately approximate the behavior of the target black-box. Conducting a set of experiments on various black-box classifiers, and different tabular and textual data classification tasks, we show that our CIE method performs better than the previous perturbation-based and rule-based explanators in terms of the descriptive accuracy (an improvement of 9.3%) and interpretability (an improvement of 8.8%) of the explanations. Subjective evaluations demonstrate that the users find the explanations of CIE more understandable and interpretable than those of the other comparison methods.

In this paper, we propose a novel method named Biomedical Confident Itemsets Explanation (BioCIE), aiming at post-hoc explanation of black-box machine learning models for biomedical text classification. Using sources of domain knowledge and a confident itemset mining method, BioCIE discretizes the decision space of a black-box into smaller subspaces and extracts semantic relationships between the input text and class labels in different subspaces. Confident itemsets discover how biomedical concepts are related to class labels in the black-box's decision space. BioCIE uses the itemsets to approximate the black-box's behavior for individual predictions. Optimizing fidelity, interpretability, and coverage measures, BioCIE produces class-wise explanations that represent decision boundaries of the black-box. Results of evaluations on various biomedical text classification tasks and black-box models demonstrated that BioCIE can outperform perturbation-based and decision set methods in terms of producing concise, accurate, and interpretable explanations. BioCIE improved the fidelity of instance-wise and class-wise explanations by 11.6% and 7.5%, respectively. It also improved the interpretability of explanations by 8%. BioCIE can be effectively used to explain how a black-box biomedical text classification model semantically relates input texts to class labels. The source code and supplementary material are available at https://github.com/mmoradi-iut/BioCIE.

In this study, an efficient strategy for fault detection and isolation (FDI) of an Industrial Gas Turbine is introduced based on ensemble learning methods. Four independent Wiener models are identified by employing plant input/output data to determine system behavior. Following that, an ensemble-based method is established, which utilizes all the Wiener models and relevant residuals to detect the faults. A fault isolation structure is then developed based on ensemble bagged tree procedure such that it is capable of isolating faults in a steady-state runtime. As a crucial goal, increasing accuracy and robustness simultaneously are mainly centered. The proposed FDI method is tested on nonlinear gas turbine simulation using real data from a combined cycle power plant. The obtained results illustrate the correctness and accuracy of the presented FDI scheme.

Automatic text summarizers can reduce the time required to read lengthy text documents by extracting the most important parts. Multi-document summarizers should produce a summary that covers the main topics of multiple related input texts to diminish the extent of redundant information. In this paper, we propose a novel summarization method named Clustering and Itemset mining based Biomedical Summarizer (CIBS). The summarizer extracts biomedical concepts from the input documents and employs an itemset mining algorithm to discover main topics. Then, it applies a clustering algorithm to put the sentences into clusters such that those in the same cluster share similar topics. Selecting sentences from all the clusters, the summarizer can produce a summary that covers a wide range of topics of the input text. Using the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) toolkit, we evaluate the performance of the CIBS method against four summarizers including a state-of-the-art method. The results show that the CIBS method can improve the performance of single- and multi-document biomedical text summarization. It is shown that the topic-based sentence clustering approach can be effectively used to increase the informative content of summaries, as well as to decrease the redundant information.