Diversify Your Datasets: Analyzing Generalization via Controlled Variance in Adversarial Datasets

Ohad Rozen, Vered Shwartz, Roee Aharoni, Ido Dagan


Abstract
Phenomenon-specific “adversarial” datasets have been recently designed to perform targeted stress-tests for particular inference types. Recent work (Liu et al., 2019a) proposed that such datasets can be utilized for training NLI and other types of models, often allowing to learn the phenomenon in focus and improve on the challenge dataset, indicating a “blind spot” in the original training data. Yet, although a model can improve in such a training process, it might still be vulnerable to other challenge datasets targeting the same phenomenon but drawn from a different distribution, such as having a different syntactic complexity level. In this work, we extend this method to drive conclusions about a model’s ability to learn and generalize a target phenomenon rather than to “learn” a dataset, by controlling additional aspects in the adversarial datasets. We demonstrate our approach on two inference phenomena – dative alternation and numerical reasoning, elaborating, and in some cases contradicting, the results of Liu et al.. Our methodology enables building better challenge datasets for creating more robust models, and may yield better model understanding and subsequent overarching improvements.
Anthology ID:
K19-1019
Volume:
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
196–205
Language:
URL:
https://www.aclweb.org/anthology/K19-1019
DOI:
10.18653/v1/K19-1019
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/K19-1019.pdf