Improving Neural Question Generation using World Knowledge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gupta, Deepak, Suleman, Kaheer, Adada, Mahmoud, McNamara, Andrew, Harris, Justin
Format: Preprint
Published: 2019
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918262134013952
author Gupta, Deepak
Suleman, Kaheer
Adada, Mahmoud
McNamara, Andrew
Harris, Justin
author_facet Gupta, Deepak
Suleman, Kaheer
Adada, Mahmoud
McNamara, Andrew
Harris, Justin
contents In this paper, we propose a method for incorporating world knowledge (linked entities and fine-grained entity types) into a neural question generation model. This world knowledge helps to encode additional information related to the entities present in the passage required to generate human-like questions. We evaluate our models on both SQuAD and MS MARCO to demonstrate the usefulness of the world knowledge features. The proposed world knowledge enriched question generation model is able to outperform the vanilla neural question generation model by 1.37 and 1.59 absolute BLEU 4 score on SQuAD and MS MARCO test dataset respectively.
format Preprint
id arxiv_https___arxiv_org_abs_1909_03716
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Improving Neural Question Generation using World Knowledge
Gupta, Deepak
Suleman, Kaheer
Adada, Mahmoud
McNamara, Andrew
Harris, Justin
Computation and Language
In this paper, we propose a method for incorporating world knowledge (linked entities and fine-grained entity types) into a neural question generation model. This world knowledge helps to encode additional information related to the entities present in the passage required to generate human-like questions. We evaluate our models on both SQuAD and MS MARCO to demonstrate the usefulness of the world knowledge features. The proposed world knowledge enriched question generation model is able to outperform the vanilla neural question generation model by 1.37 and 1.59 absolute BLEU 4 score on SQuAD and MS MARCO test dataset respectively.
title Improving Neural Question Generation using World Knowledge
topic Computation and Language
url https://arxiv.org/abs/1909.03716