ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data
This work addresses the problem of event forecasting from temporal text data for researchers in NLP and AI, by introducing a new dataset and benchmark, though it is incremental as it builds on existing QA and forecasting methods.
The authors tackled event forecasting by formulating it as a restricted-domain multiple-choice QA task using unstructured text data, creating the ForecastQA dataset with 10,392 questions, and found that their best BERT-based model achieved 60.1% accuracy, lagging 19% behind human performance.
Event forecasting is a challenging, yet important task, as humans seek to constantly plan for the future. Existing automated forecasting studies rely mostly on structured data, such as time-series or event-based knowledge graphs, to help predict future events. In this work, we aim to formulate a task, construct a dataset, and provide benchmarks for developing methods for event forecasting with large volumes of unstructured text data. To simulate the forecasting scenario on temporal news documents, we formulate the problem as a restricted-domain, multiple-choice, question-answering (QA) task. Unlike existing QA tasks, our task limits accessible information, and thus a model has to make a forecasting judgement. To showcase the usefulness of this task formulation, we introduce ForecastQA, a question-answering dataset consisting of 10,392 event forecasting questions, which have been collected and verified via crowdsourcing efforts. We present our experiments on ForecastQA using BERT-based models and find that our best model achieves 60.1% accuracy on the dataset, which still lags behind human performance by about 19%. We hope ForecastQA will support future research efforts in bridging this gap.