A parse tree based computation technique for generating comprehension style questions from Chinese text

Andrew Kwok-Fai Lui, Sin Chun Ng, Yin Chun Fung

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper describes our research and development work on a computational method that takes a piece of Chinese unstructured text and generates a set of questions and answers as the output. Our method is largely based on Heilman & Smith's over-generation approach [1] and is included with techniques specific for handling Chinese text. Using the syntactic and semantic features identified in a sentence, various question types can be generated with answers also available. Automatic question generation is potentially a key component in future intelligent e-learning systems, but it is also a very challenging problem. A major objective of this work is to investigate technical issues and limitations that would provide direction of future research.

Original languageEnglish
Title of host publicationTechnology in Education
Subtitle of host publicationTransforming Educational Practices with Technology - 1st International Conference, ICTE 2014, Revised Selected Papers
EditorsKam Cheong Li, Simon K.S. Cheung, Tak-Lam Wong, Jeanne Lam, Kwan Keung Ng
Pages61-73
Number of pages13
ISBN (Electronic)9783662461570
DOIs
Publication statusPublished - 2015
Event1st International Conference on Technology in Education, ICTE 2014 - Hong Kong, China
Duration: 2 Jul 20144 Jul 2014

Publication series

NameCommunications in Computer and Information Science
Volume494
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference1st International Conference on Technology in Education, ICTE 2014
Country/TerritoryChina
CityHong Kong
Period2/07/144/07/14

Keywords

  • Online learning
  • Question generation
  • Question taxonomy

Fingerprint

Dive into the research topics of 'A parse tree based computation technique for generating comprehension style questions from Chinese text'. Together they form a unique fingerprint.

Cite this