| Surface Form Competition: Why the Highest Probability Answer Isn’t Always Right | Nov 1, 2021 | FormMultiple-choice | CodeCode Available | 1 |
| MixQG: Neural Question Generation with Mixed Answer Types | Oct 15, 2021 | Multiple-choiceQuestion Answering | CodeCode Available | 1 |
| A Few More Examples May Be Worth Billions of Parameters | Oct 8, 2021 | Extractive Question-AnsweringMultiple-choice | CodeCode Available | 1 |
| An MRC Framework for Semantic Role Labeling | Sep 14, 2021 | Computational EfficiencyMachine Reading Comprehension | CodeCode Available | 1 |
| ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization | Sep 9, 2021 | Abstractive Text SummarizationDecoder | CodeCode Available | 1 |
| General-Purpose Question-Answering with Macaw | Sep 6, 2021 | Generative Question AnsweringMultiple-choice | CodeCode Available | 1 |
| TIMEDIAL: Temporal Commonsense Reasoning in Dialog | Jun 8, 2021 | Multiple-choiceTimedial | CodeCode Available | 1 |
| NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation | May 30, 2021 | Dialogue State TrackingMultiple-choice | CodeCode Available | 1 |
| Option Tracing: Beyond Correctness Analysis in Knowledge Tracing | Apr 19, 2021 | Knowledge TracingMultiple-choice | CodeCode Available | 1 |
| When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset | Apr 18, 2021 | Multiple-choiceQuestion Answering | CodeCode Available | 1 |
