Interpretable deep learning: Interpretation, interpretability, trustworthiness, and beyond
Deep neural networks have been well-known for their superb handling of various machine
learning and artificial intelligence tasks. However, due to their over-parameterized black-box …
learning and artificial intelligence tasks. However, due to their over-parameterized black-box …
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 …
A survey of the state of explainable AI for natural language processing
Recent years have seen important advances in the quality of state-of-the-art models, but this
has come at the expense of models becoming less interpretable. This survey presents an …
has come at the expense of models becoming less interpretable. This survey presents an …
Does the whole exceed its parts? the effect of ai explanations on complementary team performance
Many researchers motivate explainable AI with studies showing that human-AI team
performance on decision-making tasks improves when the AI explains its recommendations …
performance on decision-making tasks improves when the AI explains its recommendations …
Towards faithfully interpretable NLP systems: How should we define and evaluate faithfulness?
A Jacovi, Y Goldberg - arXiv preprint arXiv:2004.03685, 2020 - arxiv.org
With the growing popularity of deep-learning based NLP models, comes a need for
interpretable systems. But what is interpretability, and what constitutes a high-quality …
interpretable systems. But what is interpretability, and what constitutes a high-quality …
Attention is not explanation
S Jain, BC Wallace - arXiv preprint arXiv:1902.10186, 2019 - arxiv.org
Attention mechanisms have seen wide adoption in neural NLP models. In addition to
improving predictive performance, these are often touted as affording transparency: models …
improving predictive performance, these are often touted as affording transparency: models …
An empirical study of spatial attention mechanisms in deep networks
Attention mechanisms have become a popular component in deep neural networks, yet
there has been little examination of how different influencing factors and methods for …
there has been little examination of how different influencing factors and methods for …
Self-attention attribution: Interpreting information interactions inside transformer
The great success of Transformer-based models benefits from the powerful multi-head self-
attention mechanism, which learns token dependencies and encodes contextual information …
attention mechanism, which learns token dependencies and encodes contextual information …
Attention interpretability across nlp tasks
The attention layer in a neural network model provides insights into the model's reasoning
behind its prediction, which are usually criticized for being opaque. Recently, seemingly …
behind its prediction, which are usually criticized for being opaque. Recently, seemingly …