Implicature and Presupposition Diagnostic dataset (IMPPRES)
Natural Language Inference (NLI)English
Created by Jeretic et al. at 2020, the Implicature and Presupposition Diagnostic dataset (IMPPRES) is a Natural Language Inference (NLI) dataset in English containing 25,000+ records in JSON format.
About Implicature and Presupposition Diagnostic dataset (IMPPRES)
Dataset contains semiautomatically generated sentence pairs illustrating well-studied pragmatic inference types. IMPPRES follows the format of SNLI, MultiNLI and XNLI, which was created to evaluate how well trained NLI models recognize several classes of presuppositions and scalar implicatures.
Details
- Task
- Natural Language Inference (NLI)
- Language
- English
- Format
- JSON
- Rows / instances
- 25,000+
- Creator
- Jeretic et al.
- Year
- 2020