eprintid: 3633
rev_number: 10
eprint_status: archive
userid: 286
dir: disk0/00/00/36/33
datestamp: 2019-11-27 13:41:43
lastmod: 2019-11-29 05:55:46
status_changed: 2019-11-27 13:41:43
type: conference_item
metadata_visibility: show
creators_name: Pham, Thi Ngan
creators_name: Ha, Quang Thuy
creators_name: Nguyen, Minh Chau
creators_name: Nguyen, Tri Thanh
creators_id: nganpt.di12@vnu.edu.vn
creators_id: thuyhq@vnu.edu.vn
creators_id: 15021766@vnu.edu.vn
creators_id: ntthanh@vnu.edu.vn
title: A probability-based close domain metric in lifelong learning for multi-label classification
ispublished: pub
subjects: IT
divisions: fac_fit
abstract: Lifelong machine learning has recently become a hot topic attracting the re-searchers all over the world by its effectiveness in dealing with current problem by exploiting the past knowledge. The combination of topic modeling on pre-vious domain knowledge (such as topic modeling with Automatically generat-ed Must-links and Cannot-links, which exploits must-link and cannot-link of two terms), and lifelong topic modeling (which employs the modeling of previous tasks) is widely used to produce better topics. This paper proposes a close domain metric based on probability to choose reliable (prior) knowledge learnt from the past to generate more coherent topics on the current domain. This knowledge is, then,  used to enrich features for multi-label classifier. Several experiments performed on review dataset of hotel show that the proposed approach leads to an improvement in performance over the baseline.
date: 2019
date_type: published
full_text_status: none
pres_type: paper
event_title: The 6th International Conference on Computer Science, Applied Mathematics and Applications (ICCSAMA 2019)
event_type: conference
refereed: FALSE
citation:   Pham, Thi Ngan and Ha, Quang Thuy and Nguyen, Minh Chau and Nguyen, Tri Thanh  (2019) A probability-based close domain metric in lifelong learning for multi-label classification.  In: The 6th International Conference on Computer Science, Applied Mathematics and Applications (ICCSAMA 2019).