Probing Language Models for Understanding of Temporal Expressions
This work addresses the need for better evaluation of temporal reasoning in NLP models, but it is incremental as it focuses on probing existing models without introducing new methods.
The authors tackled the problem of evaluating language models' understanding of temporal expressions by creating three NLI challenge sets, finding that models fine-tuned on MNLI have basic perception of time order but lack thorough understanding of temporal relations.
We present three Natural Language Inference (NLI) challenge sets that can evaluate NLI models on their understanding of temporal expressions. More specifically, we probe these models for three temporal properties: (a) the order between points in time, (b) the duration between two points in time, (c) the relation between the magnitude of times specified in different units. We find that although large language models fine-tuned on MNLI have some basic perception of the order between points in time, at large, these models do not have a thorough understanding of the relation between temporal expressions.