Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension

Max Bartolo, Alastair Roberts, Johannes Welbl, Sebastian Riedel, Pontus Stenetorp


Abstract
Innovations in annotation methodology have been a catalyst for Reading Comprehension (RC) datasets and models. One recent trend to challenge current RC models is to involve a model in the annotation process: Humans create questions adversarially, such that the model fails to answer them correctly. In this work we investigate this annotation methodology and apply it in three different settings, collecting a total of 36,000 samples with progressively stronger models in the annotation loop. This allows us to explore questions such as the reproducibility of the adversarial effect, transfer from data collected with varying model-in-the-loop strengths, and generalization to data collected without a model. We find that training on adversarially collected samples leads to strong generalization to non-adversarially collected datasets, yet with progressive performance deterioration with increasingly stronger models-in-the-loop. Furthermore, we find that stronger models can still learn from datasets collected with substantially weaker models-in-the-loop. When trained on data collected with a BiDAF model in the loop, RoBERTa achieves 39.9F1 on questions that it cannot answer when trained on SQuAD—only marginally lower than when trained on data collected using RoBERTa itself (41.0F1).
Anthology ID:
2020.tacl-1.43
Volume:
Transactions of the Association for Computational Linguistics, Volume 8
Month:
Year:
2020
Address:
Cambridge, MA
Editors:
Mark Johnson, Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
662–678
Language:
URL:
https://aclanthology.org/2020.tacl-1.43
DOI:
10.1162/tacl_a_00338
Bibkey:
Cite (ACL):
Max Bartolo, Alastair Roberts, Johannes Welbl, Sebastian Riedel, and Pontus Stenetorp. 2020. Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension. Transactions of the Association for Computational Linguistics, 8:662–678.
Cite (Informal):
Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension (Bartolo et al., TACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.tacl-1.43.pdf