Human-in-the-loop Debugging Deep Text Classifiers

By Piyawat Lertvittayakumjorn, Lucia Specia, Francesca Toni. 2020

57 citations recorded by the source corpus.

Since obtaining a perfect training dataset (i.e., a dataset which is considerably large, unbiased, and well-representative of unseen cases) is hardly possible, many real-world text classifiers are trained on the available, yet imperfect, datasets. These classifiers are thus likely to have undesirable properties. For instance, they may have biases against some sub-populations or may not work effectively in the wild due to overfitting. In this paper, we propose FIND – a framework which enables humans to debug deep learning text classifiers by disabling irrelevant hidden features. Experiments show that by using FIND, humans can improve CNN text classifiers which were trained under different types of imperfect datasets (including datasets with biases and datasets with dissimilar train-test distributions).

Subfields: Artificial Intelligence, Natural Language Processing

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

In Natural Language Processing

Citations in the corpus

Refining Language Models with Compositional Explanations (2021, methodology): “A more interpretable direction is to associate features with specific labels as a source of supervision [32], or let users suggest adjustments of low-level features by examining model explanations [24, 43, 26].”
Post-hoc Concept Bottleneck Models (2022, background): “FIND (Lertvittayakumjorn et al., 2020) prunes individual neurons chosen by users and later fine-tunes the model.”