Semi-structured data, such as Infobox tables, often include temporal information about entities, either implicitly or explicitly. Can current NLP systems reason about such information in semi-structured tables? To tackle this question, we introduce the task of temporal question answering on semi-structured tables. We present a dataset, TempTabQA, which comprises 11,454 question-answer pairs extracted from 1,208 Wikipedia Infobox tables spanning more than 90 distinct domains. Using this dataset, we evaluate several state-of-the-art models for temporal reasoning. We observe that even the top-performing LLMs lag behind human performance by more than 13.5 F1 points. Given these results, our dataset has the potential to serve as a challenging benchmark to improve the temporal reasoning capabilities of NLP models.
@article{arxiv.2311.08002,
title = {TempTabQA: Temporal Question Answering for Semi-Structured Tables},
author = {Vivek Gupta and Pranshu Kandoi and Mahek Bhavesh Vora and Shuo Zhang and Yujie He and Ridho Reinanda and Vivek Srikumar},
journal= {arXiv preprint arXiv:2311.08002},
year = {2023}
}