TY - GEN
T1 - Semi-unsupervised lifelong learning for sentiment classification
T2 - 3rd High Performance Computing and Cluster Technologies Conference, HPCCT 2019 and the 2nd International Conference on Big Data and Artificial Intelligence, BDAI 2019
AU - Hong, Xianbin
AU - Pal, Gautam
AU - Guan, Sheng Uei
AU - Wong, Prudence
AU - Liu, Dawei
AU - Man, Ka Lok
AU - Huang, Xin
N1 - Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/6/22
Y1 - 2019/6/22
N2 - Lifelong machine learning is a novel machine learning paradigm which can continually accumulate knowledge during learning. The knowledge extracting and reusing abilities enable the lifelong machine learning to solve the related problems. The traditional approaches like Naïve Bayes and some neural network based approaches only aim to achieve the best performance upon a single task. Unlike them, the lifelong machine learning in this paper focus on how to accumulate knowledge during learning and leverage them for the further tasks. Meanwhile, the demand for labeled data for training also be significantly decreased with the knowledge reusing. This paper suggests that the aim of the lifelong learning is to use less labeled data and computational cost to achieve the performance as well as or even better than the supervised learning.
AB - Lifelong machine learning is a novel machine learning paradigm which can continually accumulate knowledge during learning. The knowledge extracting and reusing abilities enable the lifelong machine learning to solve the related problems. The traditional approaches like Naïve Bayes and some neural network based approaches only aim to achieve the best performance upon a single task. Unlike them, the lifelong machine learning in this paper focus on how to accumulate knowledge during learning and leverage them for the further tasks. Meanwhile, the demand for labeled data for training also be significantly decreased with the knowledge reusing. This paper suggests that the aim of the lifelong learning is to use less labeled data and computational cost to achieve the performance as well as or even better than the supervised learning.
KW - Lifelong machine learning
KW - Sentiment classification
UR - http://www.scopus.com/inward/record.url?scp=85071562385&partnerID=8YFLogxK
U2 - 10.1145/3341069.3342992
DO - 10.1145/3341069.3342992
M3 - Conference Proceeding
AN - SCOPUS:85071562385
T3 - ACM International Conference Proceeding Series
SP - 87
EP - 93
BT - HPCCT 2019 - 3rd High Performance Computing and Cluster Technologies Conference and BDAI 2019 - 2nd International Conference on Big Data and Artificial Intelligence
PB - Association for Computing Machinery
Y2 - 22 June 2019 through 24 June 2019
ER -