Interpreting Predictions of NLP Models
By Eric Wallace, Matt Gardner, Sameer Singh. 2020
38 citations recorded by the source corpus.
Although neural NLP models are highly expressive and empirically successful, they also systematically fail in counterintuitive ways and are opaque in their decision-making process. This tutorial will provide a background on interpretation techniques, i.e., methods for explaining the predictions of NLP models. We will first situate example-specific interpretations in the context of other ways to understand models (e.g., probing, dataset analyses). Next, we will present a thorough study of example-specific interpretations, including saliency maps, input perturbations (e.g., LIME, input reduction), adversarial attacks, and influence functions. Alongside these descriptions, we will walk through source code that creates and visualizes interpretations for a diverse set of NLP tasks. Finally, we will discuss open problems in the field, e.g., evaluating, extending, and improving interpretation methods.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- A. P. Sarath Chandar
- Siva Reddy
- Andreas Madsen
- Danqi Chen
- Luke S. Zettlemoyer
- Mohit Bansal
- Mirella Lapata
- Q. Liao
Citations in the corpus
- Post-hoc Interpretability for Neural NLP: A Survey (2021, result): “In contrast to other surveys and tutorials on interpretability methods [14, 15, 17, 25, 35, 79, 113, 119, 125] which only discusses the most popular approaches (usually 3 among input features , adversarial examples , influential examples , projection , and linguistic information ), this survey…”