The WikiText language modeling dataset is a collection of over 100 million tokens extracted from the set of verified Good and Featured articles on Wikipedia. The dataset is available under the Creative Commons Attribution-ShareAlike License.
808 PAPERS • 3 BENCHMARKS
The Corpus of Linguistic Acceptability (CoLA) consists of 10657 sentences from 23 linguistics publications, expertly annotated for acceptability (grammaticality) by their original authors. The public version contains 9594 sentences belonging to training and development sets, and excludes 1063 sentences belonging to a held out test set.
618 PAPERS • 3 BENCHMARKS
HeadQA is a multi-choice question answering testbed to encourage research on complex reasoning. The questions come from exams to access a specialized position in the Spanish healthcare system, and are challenging even for highly specialized humans.
19 PAPERS • NO BENCHMARKS YET