We present the Natural Questions corpus, a question answering dataset. Questions consist of real anonymized, aggregated queries issued to the Google search engine. An annotator is presented with a question along with a Wikipedia page from the top 5 search results, and annotates a long answer (typically a paragraph) and a short answer (one or more entities) if present on the page, or marks null if no long/short answer is present. The public release consists of 307,373 training examples with single annotations, 7,830 examples with 5-way annotations for development data, and a further 7,842 examples 5-way annotated sequestered as test data. We present experiments validating quality of the data. We also describe analysis of 25-way annotations on 302 examples, giving insights into human variability on the annotation task. We introduce robust metrics for the purposes of evaluating question answering systems; demonstrate high human upper bounds on these metrics; and establish baseline results using competitive methods drawn from related literature.

PDF Abstract Transactions of 2019 PDF Transactions of 2019 Abstract

Results from the Paper


Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Question Answering Natural Questions (long) DecAtt + DocReader F1 54.8 # 7
Question Answering Natural Questions (short) DecAtt + DocReader F1 31.4 # 6

Methods


No methods listed for this paper. Add relevant methods here