Skip to content
Branch: master
Find file History
Latest commit b2439fe Jul 26, 2019
Type Name Latest commit message Commit time
Failed to load latest commit information.
src/main Small Evaluation with 7 questions (answertypes: res, bool, date, numb… Jan 10, 2017 Update Jul 26, 2019
pom.xml Some system and loading fixes + started to rework the READMEs Apr 10, 2019

Question answering datasets

NOTE: PARL.AI does a tremendous job in including different tasks. Thus it would make sense to analyze their state before starting to include more tasks

This collection includes the following datasets or respectivly looks at the following datasets to be included:

in production (adding answers):

Overview articles:

QA datasets to analyze:

out of scope (?) :

Su, Y., Sun, H., Sadler, B., Srivatsa, M., Gur, I., Yan, Z., and Yan, X. (2016). On generating characteristic-rich question sets for QA evaluation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA, November 1-4, 2016, pages 562–572.

DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs


This collection aims at becoming a central focus point of question answering research. Using deeper analysis (sentiment, clustering, topic) of a questions will help to understand arising difficulties within QA systems. Moreover, this collection will help also semantic search, e.g. keyword search, phrase search, in later stages.

Maven Dependency

This library is available as snapshot here:


Add the following repository:

			<name>University Leipzig, AKSW Maven2 Repository</name>
			<name>University Leipzig, AKSW Maven2 Repository</name>

Look for more interesting libraries here:


You can’t perform that action at this time.