Evaluating NLP Models via Contrast Sets

by   Matt Gardner, et al.

Standard test sets for supervised learning evaluate in-distribution generalization. Unfortunately, when a dataset has systematic gaps (e.g., annotation artifacts), these evaluations are misleading: a model can learn simple decision rules that perform well on the test set but do not capture a dataset's intended capabilities. We propose a new annotation paradigm for NLP that helps to close systematic gaps in the test data. In particular, after a dataset is constructed, we recommend that the dataset authors manually perturb the test instances in small but meaningful ways that (typically) change the gold label, creating contrast sets. Contrast sets provide a local view of a model's decision boundary, which can be used to more accurately evaluate a model's true linguistic capabilities. We demonstrate the efficacy of contrast sets by creating them for 10 diverse NLP datasets (e.g., DROP reading comprehension, UD parsing, IMDb sentiment analysis). Although our contrast sets are not explicitly adversarial, model performance is significantly lower on them than on the original test sets—up to 25% in some cases. We release our contrast sets as new evaluation benchmarks and encourage future dataset construction efforts to follow similar annotation processes.



page 1


Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA

Recent works have shown that supervised models often exploit data artifa...

Break, Perturb, Build: Automatic Perturbation of Reasoning Paths through Question Decomposition

Recent efforts to create challenge benchmarks that test the abilities of...

DuReaderrobust: A Chinese Dataset Towards Evaluating the Robustness of Machine Reading Comprehension Models

Machine Reading Comprehension (MRC) is a crucial and challenging task in...

Benchmarking Robustness of Machine Reading Comprehension Models

Machine Reading Comprehension (MRC) is an important testbed for evaluati...

Linguistically-Informed Transformations (LIT): A Method forAutomatically Generating Contrast Sets

Although large-scale pretrained language models, such as BERT and RoBERT...

Handling Missing Annotations in Supervised Learning Data

Data annotation is an essential stage in supervised learning. However, t...

Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks

Labelled data is the foundation of most natural language processing task...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.