Datasets › NarrativeQA

NarrativeQA

Introduced by Tomáš Kočiský et al. in The NarrativeQA Reading Comprehension Challenge19 Dec 2017 archive 2025-07-28

The NarrativeQA dataset includes a list of documents with Wikipedia summaries, links to full stories, and questions and answers.

Source: DeepMind Image Source: Kočiský et al

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Question Answering NarrativeQA Masque (NarrativeQA + MS MARCO) Rouge-L 59.87 Multi-style Generative Reading Comprehension — 10 Compare

Papers archive 2025-07-28

9 shown of 9 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 206. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Distilling Knowledge from Reader to Retriever for Question Answering 4 1 8 Dec 2020 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
A Discrete Hard EM Approach for Weakly Supervised Question Answering 1 1 11 Sep 2019 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Multi-style Generative Reading Comprehension 0 2 8 Jan 2019 not harvested
Densely Connected Attention Propagation for Reading Comprehension 2 1 10 Nov 2018 not harvested
Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension 0 1 1 Oct 2018 not harvested
Cut to the Chase: A Context Zoom-in Network for Reading Comprehension 0 1 1 Oct 2018 not harvested
Commonsense for Generative Multi-Hop Question Answering Tasks 2 1 17 Sep 2018 ran 0 of 7 samples (7 unverified)
The NarrativeQA Reading Comprehension Challenge 2 1 19 Dec 2017 not harvested
Bidirectional Attention Flow for Machine Comprehension 27 1 5 Nov 2016 ran 8 of 11 samples (3 unverified; 7 pointer-only for licence)

Dataset loaders archive 2025-07-28

5 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Apache-2.0 License

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • NarrativeQA

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections