Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
The Multi-Genre NLI Corpus (MultiNLI)¶
General Language Understanding Evaluation (GLUE)¶
The Stanford Question Answering Dataset¶
SWAG (Situations With Adversarial Generations)¶
Reading Comprehension Dataset (RACE)¶
Heuristic Analysis for NLI Systems Data set (HANS)¶
The Cross-Lingual NLI Corpus (XNLI)¶
Standford NLP - Sentiment Treebank¶
WordNet¶
CoLA: The Corpus of Linguistic Acceptability¶
References¶
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Swag: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference