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 the abilities a dataset is intended to test. We propose a more rigorous 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, and 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.

Existing temporal relation (TempRel) annotation schemes often have low interannotator agreements (IAA) even between experts, suggesting that the current annotation task needs a better definition. This paper proposes a new multi-axis modeling to better capture the temporal structure of events. In addition, we identify that event end-points are a major source of confusion in annotation, so we also propose to annotate TempRels based on start-points only. A pilot expert annotation effort using the proposed scheme shows significant improvement in IAA from the conventional 60's to 80's (Cohen's Kappa). This better-defined annotation scheme further enables the use of crowdsourcing to alleviate the labor intensity for each annotator. We hope that this work can foster more interesting studies towards event understanding. 1 This paper proposes a new approach to handling

Identifying temporal relations between events is an essential step towards natural language understanding. However, the temporal relation between two events in a story depends on, and is often dictated by, relations among other events. Consequently, effectively identifying temporal relations between events is a challenging problem even for human annotators. This paper suggests that it is important to take these dependencies into account while learning to identify these relations and proposes a structured learning approach to address this challenge. As a byproduct, this provides a new perspective on handling missing relations, a known issue that hurts existing methods. As we show, the proposed approach results in significant improvements on the two commonly used data sets for this problem.

Understanding time is crucial for understanding events expressed in natural language. Because people rarely say the obvious, it is often necessary to have commonsense knowledge about various temporal aspects of events, such as duration, frequency, and temporal order. However, this important problem has so far received limited attention. This paper systematically studies this temporal commonsense problem. Specifically, we define five classes of temporal commonsense, and use crowdsourcing to develop a new dataset, MCTACO , that serves as a test set for this task. We find that the best current methods used on MCTACO are still far behind human performance, by about 20%, and discuss several directions for improvement. We hope that the new dataset and our study here can foster more future research on this topic. 1 1 The dataset, annotation interfaces, guidelines, and qualification tests are available at:

Understanding temporal and causal relations between events is a fundamental natural language understanding task. Because a cause must occur earlier than its effect, temporal and causal relations are closely related and one relation often dictates the value of the other. However, limited attention has been paid to studying these two relations jointly. This paper presents a joint inference framework for them using constrained conditional models (CCMs). Specifically, we formulate the joint problem as an integer linear programming (ILP) problem, enforcing constraints that are inherent in the nature of time and causality. We show that the joint inference framework results in statistically significant improvement in the extraction of both temporal and causal relations from text. 1