SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations

Xiang Kong, Eduard Hovy, Varun Gangal

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

shawnkx/SCDE — marked official in Papers with Code; named in the paper
karins/CoherenceFramework

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce SCDE, a dataset to evaluate the performance of computational models through sentence prediction. SCDE is a humancreated 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. 1 2

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2004.12934")
get_code_for_paper("2004.12934")
have("2004.12934")

Connect an agent — have() is free.