relation: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/4180/
title: A Targeted Topic Model based Multi-Label   Deep Learning Classification Framework   for Aspect-based Opinion Mining
creator: Nguyen, Thi Cham
creator: Pham, Thi Ngan
creator: Le, Hoang Quynh
creator: Nguyen, Tri Thanh
creator: Bui, Hong Nhung
creator: Ha, Quang Thuy
subject: ISI/Scopus indexed conference
description: Recently, deep Convolutional Neural Network (CNN) model has achieved remarkable results in Natural Language Processing (NLP) tasks, such as information retrieval, relation classification, semantic parsing, sentence modeling and other traditional NLP tasks, etc. On the other hand, topic modeling method has been proved to be effective by exploiting hidden knowledge in a corpus of documents. Motivated from these successes, we propose a framework that takes advantages of closure domain measure to get enriched knowledge from close domains to the dataset of the current task to improve the CNN model, and apply a Targeted Topic Model to take more detailed exploration on each labeled aspect of an opinion. Experimental results on different scenarios show the effectiveness of the proposed framework for multi-label classification task in comparison to other related models on the same Hotel review dataset.
date: 2020-11-12
type: Conference or Workshop Item
type: NonPeerReviewed
format: application/pdf
language: en
identifier: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/4180/2/KSE.pdf
identifier:   Nguyen, Thi Cham and Pham, Thi Ngan and Le, Hoang Quynh and Nguyen, Tri Thanh and Bui, Hong Nhung and Ha, Quang Thuy  (2020) A Targeted Topic Model based Multi-Label Deep Learning Classification Framework for Aspect-based Opinion Mining.  In: The 12th IEEE International Conference on KNOWLEDGE AND SYSTEMS ENGINEERING ( KSE 2020), November 12-14, 2020, Cần Thơ, Việt Nam.     
relation: https://kse-conference.org/