AI Information

가장 language modeling의 평가를 척도하는 기본이 되는 리더보드. https://gluebenchmark.com/leaderboard Multi-task Glue benchmark https://decanlp.com/   논문:  https://arxiv.org/abs/1804.07461

Question answering Question answering is the task of answering a question. Table of contents ARC ShARC Reading comprehension CliCR CNN / Daily Mail CoQA HotpotQA MS MARCO MultiRC NewsQA QAngaroo QuAC RACE SQuAD Story Cloze Test Recipe QA NarrativeQA DuoRC DROP Open-domain Question Answering DuReader Quasar SearchQA Knowledge Base Question Answering ARC The  AI2 Reasoning Challenge (ARC)  dataset is a question answering, which contains 7,787 genuine grade-school level, multiple-choice science questions. The dataset is partitioned into a Challenge Set and an Easy Set. The Challenge Set contains only questions answered incorrectly by both a retrieval-based algorithm and a word co-occurrence algorithm. Models are evaluated based on accuracy. A public leaderboard is available on the  ARC website . ShARC ShARC  is a challenging QA dataset that requires logical reasoning, elements of entailment/NLI and natural language generation...