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.
%0 Generic
%1 choi2018question
%A Choi, Eunsol
%A He, He
%A Iyyer, Mohit
%A Yatskar, Mark
%A Yih, Wen-tau
%A Choi, Yejin
%A Liang, Percy
%A Zettlemoyer, Luke
%D 2018
%K dataset masterthesis qna
%T QuAC : Question Answering in Context
%U http://arxiv.org/abs/1808.07036
%X 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.
@misc{choi2018question,
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.},
added-at = {2020-09-11T09:53:05.000+0200},
author = {Choi, Eunsol and He, He and Iyyer, Mohit and Yatskar, Mark and Yih, Wen-tau and Choi, Yejin and Liang, Percy and Zettlemoyer, Luke},
biburl = {https://www.bibsonomy.org/bibtex/273408cd1bfc5d4a4d362ad488476209e/festplatte},
description = {[1808.07036] QuAC : Question Answering in Context},
interhash = {977abfae3272d388151fb523ebeaa0a0},
intrahash = {73408cd1bfc5d4a4d362ad488476209e},
keywords = {dataset masterthesis qna},
note = {EMNLP Camera Ready},
timestamp = {2021-02-11T14:20:12.000+0100},
title = {QuAC : Question Answering in Context},
url = {http://arxiv.org/abs/1808.07036},
year = 2018
}