ForecastQA: A Question Answering Challenge for Event Forecasting

Event forecasting is a challenging, yet consequential task, as humans seek to constantly plan for the future. Existing automated forecasting approaches rely mostly on structured data, such as time-series or event-based knowledge graphs, to help predict future events. In this work, we formulate the forecasting problem as a restricted-domain, multiple-choice, question-answering (QA) task that simulates the forecasting scenario. To showcase the usefulness of this task formulation, we introduce a dataset ForecastQA, a question-answering dataset consisting of 10,392 event forecasting questions, which have been collected and verified via crowdsourcing efforts. We also present our experiments on ForecastQA using BERT-based models and find that our best model achieves 61.0\% accuracy on the dataset, which is still far behind human performance by about 18%. We hope ForecastQA will support future research efforts in bridging this gap.