| WIQA: A dataset for ``What if...'' reasoning over procedural text | Nov 1, 2019 | Multiple-choice | —Unverified | 0 |
| Social IQa: Commonsense Reasoning about Social Interactions | Nov 1, 2019 | Multiple-choiceQuestion Answering | —Unverified | 0 |
| Answering questions by learning to rank - Learning to rank by answering questions | Nov 1, 2019 | ARCLearning-To-Rank | —Unverified | 0 |
| Evaluating Question Answering Evaluation | Nov 1, 2019 | Answer GenerationMultiple-choice | —Unverified | 0 |
| Sentence Embeddings for Russian NLU | Oct 29, 2019 | Multiple-choiceParaphrase Identification | CodeCode Available | 0 |
| What does BERT Learn from Multiple-Choice Reading Comprehension Datasets? | Oct 28, 2019 | Multiple-choiceReading Comprehension | —Unverified | 0 |
| QASC: A Dataset for Question Answering via Sentence Composition | Oct 25, 2019 | Common Sense ReasoningMulti-hop Question Answering | CodeCode Available | 0 |
| Good, Better, Best: Textual Distractors Generation for Multiple-Choice Visual Question Answering via Reinforcement Learning | Oct 21, 2019 | Data AugmentationDecision Making | —Unverified | 0 |
| MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension | Oct 1, 2019 | Logical ReasoningMachine Reading Comprehension | CodeCode Available | 0 |
| Teaching Pretrained Models with Commonsense Reasoning: A Preliminary KB-Based Approach | Sep 20, 2019 | Few-Shot LearningLogical Reasoning | —Unverified | 0 |
