DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs

Dheeru Dua, Yizhong Wang, Pradeep Dasigi, Gabriel Stanovsky, Sameer Singh, Matt Gardner


Abstract
Reading comprehension has recently seen rapid progress, with systems matching humans on the most popular datasets for the task. However, a large body of work has highlighted the brittleness of these systems, showing that there is much work left to be done. We introduce a new reading comprehension benchmark, DROP, which requires Discrete Reasoning Over the content of Paragraphs. In this crowdsourced, adversarially-created, 55k-question benchmark, a system must resolve references in a question, perhaps to multiple input positions, and perform discrete operations over them (such as addition, counting, or sorting). These operations require a much more comprehensive understanding of the content of paragraphs, as they remove the paraphrase-and-entity-typing shortcuts available in prior datasets. We apply state-of-the-art methods from both the reading comprehension and semantic parsing literatures on this dataset and show that the best systems only achieve 38.4% F1 on our generalized accuracy metric, while expert human performance is 96%. We additionally present a new model that combines reading comprehension methods with simple numerical reasoning to achieve 51% F1.
Anthology ID:
N19-1246
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2368–2378
Language:
URL:
https://www.aclweb.org/anthology/N19-1246
DOI:
10.18653/v1/N19-1246
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/N19-1246.pdf
Supplementary:
 N19-1246.Supplementary.pdf