Children’s Book Test (CBT)
Question AnsweringReading ComprehensionEnglish
Children’s Book Test (CBT) is a question answering dataset in English from Hill et al. with ~688,000 records in Text format.
About Children’s Book Test (CBT)
Dataset contains ‘questions’ from chapters in the book by enumerating 21 consecutive sentences. In each question, the first 20 sentences form the context, and a word is removed from the 21st sentence, which becomes the query. Models must identify the answer word among a selection of 10 candidate answers appearing in the context sentences and the query.
Details
- Task
- Question Answering, Reading Comprehension
- Language
- English
- Format
- Text
- Rows / instances
- ~688,000
- Creator
- Hill et al.
- Year
- 2016