eprintid: 1885
rev_number: 10
eprint_status: archive
userid: 290
dir: disk0/00/00/18/85
datestamp: 2016-11-14 02:32:51
lastmod: 2016-11-14 02:32:51
status_changed: 2016-11-14 02:32:51
type: conference_item
metadata_visibility: show
creators_name: Le, Hong Phuong
creators_name: Phan, Xuan Hieu
creators_name: Nguyen, Tien Dung
creators_id: hieupx@vnu.edu.vn
title: Using Dependency Analysis to Improve Question Classification
ispublished: pub
subjects: IT
divisions: fac_fit
abstract: Question classification is a first necessary task of automatic question
answering systems. Linguistic features play an important role in developing an accurate question classifier. This paper proposes to use typed dependencies which are extracted automatically from dependency parses of questions to improve accuracy of classification. Experiment results show that with only surface typed dependencies,
one can improve the accuracy of a discriminative question classifier by over 8.0% on two benchmark datasets.
date: 2014-10
date_type: published
official_url: http://doi.org/10.1007/978-3-319-11680-8_52
id_number: doi:10.1007/978-3-319-11680-8_52
contact_email: hieupx@vnu.edu.vn
full_text_status: restricted
pres_type: paper
volume: 326
pagerange: 653-665
event_title: The 8th International Conference on Knowledge and Systems Engineering (KSE)
event_location: Hanoi, Vietnam
event_dates: 9-11 October 2014
event_type: conference
refereed: TRUE
issn: 2194-5357
book_title: Knowledge and Systems Engineering
funders: FPT Technology Research Institute
citation:   Le, Hong Phuong and Phan, Xuan Hieu and Nguyen, Tien Dung  (2014) Using Dependency Analysis to Improve Question Classification.  In: The 8th International Conference on Knowledge and Systems Engineering (KSE), 9-11 October 2014, Hanoi, Vietnam.     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/1885/1/10.1007%252F978-3-319-11680-8_52