eprintid: 3411
rev_number: 11
eprint_status: archive
userid: 405
dir: disk0/00/00/34/11
datestamp: 2019-01-09 13:53:05
lastmod: 2019-01-09 13:53:05
status_changed: 2019-01-09 13:53:05
type: conference_item
metadata_visibility: show
creators_name: Bui, Van Tan
creators_name: Nguyen, Phuong Thai
creators_name: Pham, Van Lam
creators_id: bvtan@uneti.edu.vn
creators_id: thainp@vnu.edu.vn
creators_id: phamvanlam1999@gmail.com
corp_creators: University of Economic and Technical Industries, Hanoi, Vietnam
corp_creators: VNU University of Engineering and Technology, Hanoi, Vietnam
corp_creators: Institute of Linguistics, Vietnam Academy of Social Sciences, Hanoi, Vietnam
title: Hypernymy Detection for Vietnamese Using Dynamic Weighting Neural Network
ispublished: pub
subjects: IT
divisions: fac_fit
abstract: The hypernymy detection problem aims to identify the "is-a" relation between words. The problem has recently been receiving attention from researchers in the field of natural language processing. So far, fairly-effective methods for hypernymy detection in English have been reported. Studies of hypernymy detection in Vietnamese have not been reported yet. In this study,
we applied a number of hypernymy detection methods based on word embeddings and supervised learning for Vietnamese. We propose an improvement on the method given by Luu Tuan Anh et al. (2016) by weighting context words proportionally to the semantic similarity between them and the hypernym. Based on Vietnamese WordNet, three datasets for hypernymy detection were built. Experimental results showed that our proposal can increase the efficiency from 8% to 10% in terms of accuracy compared to the original method.
date: 2018
date_type: published
full_text_status: public
pres_type: paper
event_title: International Conference on Computational Linguistics and Intelligent Text Processing
event_type: conference
refereed: FALSE
citation:   Bui, Van Tan and Nguyen, Phuong Thai and Pham, Van Lam  (2018) Hypernymy Detection for Vietnamese Using Dynamic Weighting Neural Network.  In: International Conference on Computational Linguistics and Intelligent Text Processing.     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3411/2/CicLing%202018.pdf