Explainable ai: A review of machine learning interpretability methods
Recent advances in artificial intelligence (AI) have led to its widespread industrial adoption,
with machine learning systems demonstrating superhuman performance in a significant …
with machine learning systems demonstrating superhuman performance in a significant …
Post-hoc interpretability for neural nlp: A survey
Neural networks for NLP are becoming increasingly complex and widespread, and there is a
growing concern if these models are responsible to use. Explaining models helps to address …
growing concern if these models are responsible to use. Explaining models helps to address …
Complexity-based prompting for multi-step reasoning
We study the task of prompting large-scale language models to perform multi-step
reasoning. Existing work shows that when prompted with a chain of thoughts (CoT) …
reasoning. Existing work shows that when prompted with a chain of thoughts (CoT) …
Model cards for model reporting
M Mitchell, S Wu, A Zaldivar, P Barnes… - Proceedings of the …, 2019 - dl.acm.org
Trained machine learning models are increasingly used to perform high-impact tasks in
areas such as law enforcement, medicine, education, and employment. In order to clarify the …
areas such as law enforcement, medicine, education, and employment. In order to clarify the …
Techniques for interpretable machine learning
Techniques for interpretable machine learning Page 1 68 COMMUNICATIONS OF THE
ACM | JANUARY 2020 | VOL. 63 | NO. 1 review articles MACHINE LEARNING IS …
ACM | JANUARY 2020 | VOL. 63 | NO. 1 review articles MACHINE LEARNING IS …
Semantics-aware BERT for language understanding
The latest work on language representations carefully integrates contextualized features into
language model training, which enables a series of success especially in various machine …
language model training, which enables a series of success especially in various machine …
Analysis methods in neural language processing: A survey
Y Belinkov, J Glass - … of the Association for Computational Linguistics, 2019 - direct.mit.edu
The field of natural language processing has seen impressive progress in recent years, with
neural network models replacing many of the traditional systems. A plethora of new models …
neural network models replacing many of the traditional systems. A plethora of new models …
Explaining the black-box model: A survey of local interpretation methods for deep neural networks
Y Liang, S Li, C Yan, M Li, C Jiang - Neurocomputing, 2021 - Elsevier
Recently, a significant amount of research has been investigated on interpretation of deep
neural networks (DNNs) which are normally processed as black box models. Among the …
neural networks (DNNs) which are normally processed as black box models. Among the …
SG-Net: Syntax-guided machine reading comprehension
For machine reading comprehension, the capacity of effectively modeling the linguistic
knowledge from the detail-riddled and lengthy passages and getting ride of the noises is …
knowledge from the detail-riddled and lengthy passages and getting ride of the noises is …
Counterfactual fairness in text classification through robustness
In this paper, we study counterfactual fairness in text classification, which asks the question:
How would the prediction change if the sensitive attribute referenced in the example were …
How would the prediction change if the sensitive attribute referenced in the example were …