Model Explainability in Deep Learning Based Natural Language Processing

Gholizadeh, Shafie; Zhou, Nengfeng

doi:10.48550/arxiv.2106.07410

Cited by 2 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, a bibliographic search was conducted for publications that employed ML techniques (excluding DL) for the classification of binary data (interictal and ictal) in humans with epilepsy. It was chosen to use ML techniques because they are more feasible for performing model explainability analysis and observing the importance of features [ 60 ]. DL models, being “black-box”, make it difficult to understand predictions and are therefore less interpretable [ 61 ].…”

Section: Related Workmentioning

confidence: 99%

Using Explainable Artificial Intelligence to Obtain Efficient Seizure-Detection Models Based on Electroencephalography Signals

Vieira,

Guedes,

Santos

et al. 2023

Sensors

View full text Add to dashboard Cite

Epilepsy is a condition that affects 50 million individuals globally, significantly impacting their quality of life. Epileptic seizures, a transient occurrence, are characterized by a spectrum of manifestations, including alterations in motor function and consciousness. These events impose restrictions on the daily lives of those affected, frequently resulting in social isolation and psychological distress. In response, numerous efforts have been directed towards the detection and prevention of epileptic seizures through EEG signal analysis, employing machine learning and deep learning methodologies. This study presents a methodology that reduces the number of features and channels required by simpler classifiers, leveraging Explainable Artificial Intelligence (XAI) for the detection of epileptic seizures. The proposed approach achieves performance metrics exceeding 95% in accuracy, precision, recall, and F1-score by utilizing merely six features and five channels in a temporal domain analysis, with a time window of 1 s. The model demonstrates robust generalization across the patient cohort included in the database, suggesting that feature reduction in simpler models—without resorting to deep learning—is adequate for seizure detection. The research underscores the potential for substantial reductions in the number of attributes and channels, advocating for the training of models with strategically selected electrodes, and thereby supporting the development of effective mobile applications for epileptic seizure detection.

show abstract

Section: Related Workmentioning

confidence: 99%

Using Explainable Artificial Intelligence to Obtain Efficient Seizure-Detection Models Based on Electroencephalography Signals

Vieira,

Guedes,

Santos

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Figure 6: Diagram of the perturbation based method (left, the figure is brought from[61]) and LRP (right, the figure is brought from[64]). Left: At each step, the least important word is removed by the saliency score using the leave-one-out technique.…”

mentioning

confidence: 99%

Interpreting Deep Learning Models in Natural Language Processing: A Review

Sun¹,

Yang²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Neural network models have achieved state-of-the-art performances in a wide range of natural language processing (NLP) tasks. However, a long-standing criticism against neural network models is the lack of interpretability, which not only reduces the reliability of neural NLP systems but also limits the scope of their applications in areas where interpretability is essential (e.g., health care applications). In response, the increasing interest in interpreting neural NLP models has spurred a diverse array of interpretation methods over recent years. In this survey, we provide a comprehensive review of various interpretation methods for neural models in NLP. We first stretch out a high-level taxonomy for interpretation methods in NLP, i.e., training-based approaches, test-based approaches and hybrid approaches. Next, we describe sub-categories in each category in detail, e.g., influence-function based methods, KNN-based methods, attention-based models, saliency-based methods, perturbation-based methods, etc. We point out deficiencies of current methods and suggest some avenues for future research.

show abstract

Model Explainability in Deep Learning Based Natural Language Processing

Cited by 2 publications

References 17 publications

Using Explainable Artificial Intelligence to Obtain Efficient Seizure-Detection Models Based on Electroencephalography Signals

Using Explainable Artificial Intelligence to Obtain Efficient Seizure-Detection Models Based on Electroencephalography Signals

Interpreting Deep Learning Models in Natural Language Processing: A Review

Contact Info

Product

Resources

About