iSEA: An Interactive Pipeline for Semantic Error Analysis of NLP Models
Authors:
Open Access
- 22 March 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 878-888
Abstract
Error analysis in NLP models is essential to successful model development and deployment. One common approach for diagnosing errors is to identify subpopulations in the dataset where the model produces the most errors. However, existing approaches typically define subpopulations based on pre-defined features, which requires users to form hypotheses of errors in advance. To complement these approaches, we propose iSEA, an Interactive Pipeline for Semantic Error Analysis in NLP Models, which automatically discovers semantically-grounded subpopulations with high error rates in the context of a human-in-the-loop interactive system. iSEA enables model developers to learn more about their model errors through discovered subpopulations, validate the sources of errors through interactive analysis on the discovered subpopulations, and test hypotheses about model errors by defining custom subpopulations. The tool supports semantic descriptions of error-prone subpopulations at the token and concept level, as well as pre-defined higher-level features. Through use cases and expert interviews, we demonstrate how iSEA can assist error understanding and analysis.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Clinical trial cohort selection based on multi-level rule-based natural language processing systemJournal of the American Medical Informatics Association, 2019
- Slice Finder: Automated Data Slicing for Model Validation2019
- Errudite: Scalable, Reproducible, and Testable Error Analysis2019
- Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference2019
- Shot Or Not: Comparison of NLP Approaches for Vaccination Behaviour Detection2018
- A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference2018
- Annotation Artifacts in Natural Language Inference Data2018
- Do Convolutional Neural Networks Learn Class Hierarchy?IEEE Transactions on Visualization and Computer Graphics, 2017
- "Why Should I Trust You?"2016
- Visual Methods for Analyzing Probabilistic Classification DataIEEE Transactions on Visualization and Computer Graphics, 2014