Extractive reading comprehension systems can often locate the correct answer
to a question in a context document, but they also tend to make unreliable
guesses on questions for which the correct answer is not stated in the context.
Existing datasets either focus exclusively on answerable questions, or use
automatically generated unanswerable questions that are easy to identify. To
address these weaknesses, we present SQuAD 2.0, the latest version of the
Stanford Question Answering Dataset (SQuAD). SQuAD 2.0 combines existing SQuAD
data with over 50,000 unanswerable questions written adversarially by
crowdworkers to look similar to answerable ones. To do well on SQuAD 2.0,
systems must not only answer questions when possible, but also determine when
no answer is supported by the paragraph and abstain from answering. SQuAD 2.0
is a challenging natural language understanding task for existing models: a
strong neural system that gets 86\% F1 on SQuAD 1.1 achieves only 66\% F1 on
SQuAD 2.0.
%0 Generic
%1 rajpurkar2018unanswerable
%A Rajpurkar, Pranav
%A Jia, Robin
%A Liang, Percy
%D 2018
%K dataset masterthesis qna squad
%T Know What You Don't Know: Unanswerable Questions for SQuAD
%U http://arxiv.org/abs/1806.03822
%X Extractive reading comprehension systems can often locate the correct answer
to a question in a context document, but they also tend to make unreliable
guesses on questions for which the correct answer is not stated in the context.
Existing datasets either focus exclusively on answerable questions, or use
automatically generated unanswerable questions that are easy to identify. To
address these weaknesses, we present SQuAD 2.0, the latest version of the
Stanford Question Answering Dataset (SQuAD). SQuAD 2.0 combines existing SQuAD
data with over 50,000 unanswerable questions written adversarially by
crowdworkers to look similar to answerable ones. To do well on SQuAD 2.0,
systems must not only answer questions when possible, but also determine when
no answer is supported by the paragraph and abstain from answering. SQuAD 2.0
is a challenging natural language understanding task for existing models: a
strong neural system that gets 86\% F1 on SQuAD 1.1 achieves only 66\% F1 on
SQuAD 2.0.
@misc{rajpurkar2018unanswerable,
abstract = {Extractive reading comprehension systems can often locate the correct answer
to a question in a context document, but they also tend to make unreliable
guesses on questions for which the correct answer is not stated in the context.
Existing datasets either focus exclusively on answerable questions, or use
automatically generated unanswerable questions that are easy to identify. To
address these weaknesses, we present SQuAD 2.0, the latest version of the
Stanford Question Answering Dataset (SQuAD). SQuAD 2.0 combines existing SQuAD
data with over 50,000 unanswerable questions written adversarially by
crowdworkers to look similar to answerable ones. To do well on SQuAD 2.0,
systems must not only answer questions when possible, but also determine when
no answer is supported by the paragraph and abstain from answering. SQuAD 2.0
is a challenging natural language understanding task for existing models: a
strong neural system that gets 86\% F1 on SQuAD 1.1 achieves only 66\% F1 on
SQuAD 2.0.},
added-at = {2020-11-22T07:51:58.000+0100},
author = {Rajpurkar, Pranav and Jia, Robin and Liang, Percy},
biburl = {https://www.bibsonomy.org/bibtex/2526538e3e1d197b6dbebd870d41bb939/festplatte},
description = {1806.03822.pdf},
interhash = {5ca29df15ac24fcbde77285f4789d921},
intrahash = {526538e3e1d197b6dbebd870d41bb939},
keywords = {dataset masterthesis qna squad},
note = {cite arxiv:1806.03822Comment: ACL 2018},
timestamp = {2021-01-23T18:14:56.000+0100},
title = {Know What You Don't Know: Unanswerable Questions for SQuAD},
url = {http://arxiv.org/abs/1806.03822},
year = 2018
}