Work

Explanation-Based Human Debugging of NLP Models: A Survey

Year: 2021

Type: article

Abstract: Debugging a machine learning model is hard since the bug usually involves the training data and the learning process. This becomes even harder for an opaque deep learning model if we have no clue about how the model actually works. In this survey, we review papers that exploit explanations to enable humans to give feedback and debug NLP models. We call this problem explanation-based human debugging (EBHD). In particular, we categorize and discuss existing work along three dimensions of EBHD (the bug context, the workflow, and the experimental setting), compile findings on how EBHD components affect the feedback providers, and highlight open problems that could be future research directions.

Source: Transactions of the Association for Computational Linguistics

DOI: 10.1162/tacl_a_00440

Authors: Piyawat Lertvittayakumjorn, Francesca Toni

Institution: Imperial College London

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

OpenAlex ID: W3159434682

FWCI: 3.432

Cites: 103

Cited by: 49

Related to: 10