Inoculation by fine-tuning: A method for analyzing challenge datasets

Nelson F. Liu, Roy Schwartz, Noah A. Smith

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

64 Scopus citations

Abstract

Several datasets have recently been constructed to expose brittleness in models trained on existing benchmarks. While model performance on these challenge datasets is significantly lower compared to the original benchmark, it is unclear what particular weaknesses they reveal. For example, a challenge dataset may be difficult because it targets phenomena that current models cannot capture, or because it simply exploits blind spots in a model's specific training set. We introduce inoculation by fine-tuning, a new analysis method for studying challenge datasets by exposing models (the metaphorical patient) to a small amount of data from the challenge dataset (a metaphorical pathogen) and assessing how well they can adapt. We apply our method to analyze the NLI “stress tests” (Naik et al., 2018) and the Adversarial SQuAD dataset (Jia and Liang, 2017). We show that after slight exposure, some of these datasets are no longer challenging, while others remain difficult. Our results indicate that failures on challenge datasets may lead to very different conclusions about models, training datasets, and the challenge datasets themselves.

Original languageAmerican English
Title of host publicationLong and Short Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages2171-2179
Number of pages9
ISBN (Electronic)9781950737130
StatePublished - 2019
Externally publishedYes
Event2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019 - Minneapolis, United States
Duration: 2 Jun 20197 Jun 2019

Publication series

NameNAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
Volume1

Conference

Conference2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019
Country/TerritoryUnited States
CityMinneapolis
Period2/06/197/06/19

Bibliographical note

Publisher Copyright:
© 2019 Association for Computational Linguistics

Fingerprint

Dive into the research topics of 'Inoculation by fine-tuning: A method for analyzing challenge datasets'. Together they form a unique fingerprint.

Cite this