TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Question Answering	SCDE	bert-large-uncased + APN	BA	0.717	# 3
Question Answering	SCDE	bert-large-uncased + APN	PA	0.299	# 3
Question Answering	SCDE	bert-large-uncased + APN	DE	0.661	# 2

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/scde-sentence-cloze-dataset-with-high-quality/question-answering-on-scde-1)](https://paperswithcode.com/sota/question-answering-on-scde-1?p=scde-sentence-cloze-dataset-with-high-quality)`

SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations

ACL 2020 · Xiang Kong, Varun Gangal, Eduard Hovy ·

We introduce SCDE, a dataset to evaluate the performance of computational models through sentence prediction. SCDE is a human-created sentence cloze dataset, collected from public school English examinations. Our task requires a model to fill up multiple blanks in a passage from a shared candidate set with distractors designed by English teachers. Experimental results demonstrate that this task requires the use of non-local, discourse-level context beyond the immediate sentence neighborhood. The blanks require joint solving and significantly impair each other's context. Furthermore, through ablations, we show that the distractors are of high quality and make the task more challenging. Our experiments show that there is a significant performance gap between advanced models (72%) and humans (87%), encouraging future models to bridge this gap.