QuAC : Question Answering in Context

TL;DR

QuAC is a new dataset for question answering in dialogue format, featuring 14,000 dialogs with open-ended, context-dependent questions, challenging existing models and highlighting the need for improved conversational QA systems.

Contribution

The paper introduces QuAC, a large-scale dataset for dialog-based question answering, and provides baseline models demonstrating the task's complexity and room for future advancements.

Findings

Best model underperforms humans by 20 F1

Questions are often unanswerable or context-dependent

Existing models struggle with dialog-specific challenges

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.