TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Question Answering	NarrativeQA	ConZNet	BLEU-1	42.76	# 5
Question Answering	NarrativeQA	ConZNet	BLEU-4	22.49	# 3
Question Answering	NarrativeQA	ConZNet	METEOR	19.24	# 4
Question Answering	NarrativeQA	ConZNet	Rouge-L	46.67	# 4

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/cut-to-the-chase-a-context-zoom-in-network/question-answering-on-narrativeqa)](https://paperswithcode.com/sota/question-answering-on-narrativeqa?p=cut-to-the-chase-a-context-zoom-in-network)`

Cut to the Chase: A Context Zoom-in Network for Reading Comprehension

EMNLP 2018 · Sathish Reddy Indurthi, Seunghak Yu, Seohyun Back, Heriberto Cuay{\'a}huitl ·

In recent years many deep neural networks have been proposed to solve Reading Comprehension (RC) tasks. Most of these models suffer from reasoning over long documents and do not trivially generalize to cases where the answer is not present as a span in a given document. We present a novel neural-based architecture that is capable of extracting relevant regions based on a given question-document pair and generating a well-formed answer. To show the effectiveness of our architecture, we conducted several experiments on the recently proposed and challenging RC dataset {`}NarrativeQA{'}. The proposed architecture outperforms state-of-the-art results by 12.62{\%} (ROUGE-L) relative improvement.

PDF Abstract