Datasets › CANARD

CANARD (A Dataset for Question-in-Context Rewriting)

Introduced by Ahmed Elgohary et al. in Can You Unpack That? Learning to Rewrite Questions-in-Context1 Nov 2019 archive 2025-07-28

CANARD is a dataset for question-in-context rewriting that consists of questions each given in a dialog context together with a context-independent rewriting of the question. The context of each question is the dialog utterences that precede the question. CANARD can be used to evaluate question rewriting models that handle important linguistic phenomena such as coreference and ellipsis resolution.

CANARD is based on QuAC (Choi et al., 2018)---a conversational reading comprehension dataset in which answers are selected spans from a given section in a Wikipedia article. Some questions in QuAC are unanswerable with their given sections. We use the answer 'I don't know.' for such questions.

CANARD is constructed by crowdsourcing question rewritings using Amazon Mechanical Turk. We apply several automatic and manual quality controls to ensure the quality of the data collection process. The dataset consists of 40,527 questions with different context lengths. More details are available in our EMNLP 2019 paper. An example is provided below. The dataset is distributed under the CC BY-SA 4.0 license.

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
Dialogue Rewriting CANARD SARG BLEU 54.80 SARG: A Novel Semi Autoregressive Generator for... NetEase-GameAI/SARG 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 1 · with a code link: 1 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran: none of the 1 papers with a benchmark row has a Syntology run on record

Page 1 of 1: paper 1 of 1 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 58. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration 1 1 4 Aug 2020 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

CC BY-SA 4.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • CANARD

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