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

Indurthi, Satish, Yu, Seunghak, Back, Seohyun and Cuayahuitl, Heriberto (2018) Cut to the Chase: A Context Zoom-in Network for Reading Comprehension. In: Empirical Methods in Natural Language Processing (EMNLP).

This is the latest version of this item.

Documents
Cut to the Chase: A Context Zoom-in Network for Reading Comprehension
[img]
[Download]
[img] PDF
sam-emnlp2018.pdf - Whole Document

294kB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

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 (Tay et al., 2018) by 12.62% (ROUGE-L) relative improvement.

Keywords:Neural networks, question answering, machine reading
Subjects:G Mathematical and Computer Sciences > G730 Neural Computing
G Mathematical and Computer Sciences > G700 Artificial Intelligence
G Mathematical and Computer Sciences > G710 Speech and Natural Language Processing
G Mathematical and Computer Sciences > G760 Machine Learning
Divisions:College of Science > School of Computer Science
ID Code:34105
Deposited On:15 Nov 2018 08:29

Available Versions of this Item

Repository Staff Only: item control page