QuAC: Question Answering in Context

TLDR

QuAC is a dataset of 14 K information‑seeking QA dialogs with 100 K questions designed for question answering in context. The dataset comprises dialogs between a student who asks free‑form questions about a hidden Wikipedia text and a teacher who answers with short text excerpts, and baseline models were evaluated on it. QuAC introduces open‑ended, sometimes unanswerable questions that depend on dialog context, and the best baseline model falls 20 F1 points behind human performance. Dataset, baseline, and leaderboard are available at http://quac.ai.

Abstract

We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total). The dialogs involve two crowd workers: (1) a student who poses a sequence of freeform questions to learn as much as possible about a hidden Wikipedia text, and (2) a teacher who answers the questions by providing short excerpts from the text. QuAC introduces challenges not found in existing machine comprehension datasets: its questions are often more open-ended, unanswerable, or only meaningful within the dialog context, as we show in a detailed qualitative evaluation. We also report results for a number of reference models, including a recently state-of-the-art reading comprehension architecture extended to model dialog context. Our best model underperforms humans by 20 F1, suggesting that there is significant room for future work on this data. Dataset, baseline, and leaderboard available at http://quac.ai.