ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data
Woojeong Jin, Rahul Khanna, Suji Kim, Dong-Ho Lee, Fred Morstatter,, Aram Galstyan, Xiang Ren

TL;DR
ForecastQA introduces a novel question-answering dataset for event forecasting from unstructured text, challenging models to predict future events with limited information, and benchmarks current methods' performance.
Contribution
The paper formulates a new event forecasting task as a multiple-choice QA problem, constructs a large dataset, and provides baseline results using BERT-based models.
Findings
Best model achieves 60.1% accuracy
Performance lags human by 19%
Dataset contains 10,392 questions
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Advanced Text Analysis Techniques · Data Quality and Management
