Read + Verify: Machine Reading Comprehension with Unanswerable Questions

Open paper
Benchmark Model Rank Results
question-answering-on-squad20Reinforced Mnemonic Reader + Answer Verifier (single model)–EM: 71.767F1: 74.295
question-answering-on-squad20-devRMR + ELMo (Model-III)–F1: 74.8EM: 72.3

Rank counts only results with a code link.