eprintid: 3149
rev_number: 6
eprint_status: archive
userid: 290
dir: disk0/00/00/31/49
datestamp: 2018-11-08 06:52:58
lastmod: 2018-11-08 06:52:58
status_changed: 2018-11-08 06:52:58
type: article
metadata_visibility: show
creators_name: Ngo, Thi Lan
creators_name: Vu, Tu
creators_name: Takeda, Hideaki
creators_name: Pham, Bao Son
creators_name: Phan, Xuan Hieu
creators_id: sonpb@vnu.edu.vn
creators_id: hieupx@vnu.edu.vn
title: Lifelong Learning Maxent for Suggestion Classification
ispublished: inpress
subjects: Scopus
divisions: fac_fit
abstract: Suggestion classification for opinion data is defined as identifying a given utterance by suggestion or non-suggestion class. In this paper, we introduce a method called LLMaxent which is the solution for the cross-domain suggestion classification. LLMaxent is a lifelong machine learning approach using maximum entropy (Maxent). In the course of lifelong learning, the drawn knowledge from the past tasks is retained and supported for the future learning. From that, we build a classifier by using labelled data in existed domains for suggestion classification in a new domain. The experimental results show that the proposed novel model can improve the performance of cross-domain suggestion classification. This is one of the preliminary research in lifelong machine learning using Maxent. Its effect is not only for suggestion classification but also for cross-domain text classification in general.
date: 2018
official_url: http://www.cys.cic.ipn.mx/cys/accepted/cicling2018
full_text_status: none
publication: Computacion y Sistemas
refereed: TRUE
issn: 1405-5546
funders: Vietnam National University, Hanoi
projects: VNU Project - QG.16.34
citation:   Ngo, Thi Lan and Vu, Tu and Takeda, Hideaki and Pham, Bao Son and Phan, Xuan Hieu  (2018) Lifelong Learning Maxent for Suggestion Classification.  Computacion y Sistemas .    ISSN 1405-5546    (In Press)