TY - GEN
T1 - A novel neural topic model and its supervised extension
AU - Cao, Ziqiang
AU - Li, Sujian
AU - Liu, Yang
AU - Li, Wenjie
AU - Ji, Heng
N1 - Publisher Copyright:
© Copyright 2015, Association for the Advancement of Artificial Intelligence (www.aaa1.org). All rights reserved.
PY - 2015/6/1
Y1 - 2015/6/1
N2 - Topic modeling techniques have the benefits of modeling words and documents uniformly under a probabilistic framework. However, they also suffer from the limitations of sensitivity to initialization and unigram topic distribution, which can be remedied by deep learning techniques. To explore the combination of topic modeling and deep learning techniques, we first explain the standard topic model from the perspective of a neural network. Based on this, we propose a novel neural topic model (NTM) where the representation of words and documents are efficiently and naturally combined into a uniform framework. Extending from NTM, we can easily add a label layer and propose the supervised neural topic model (sNTM) to tackle supervised tasks. Experiments show that our models are competitive in both topic discovery and classification/regression tasks.
AB - Topic modeling techniques have the benefits of modeling words and documents uniformly under a probabilistic framework. However, they also suffer from the limitations of sensitivity to initialization and unigram topic distribution, which can be remedied by deep learning techniques. To explore the combination of topic modeling and deep learning techniques, we first explain the standard topic model from the perspective of a neural network. Based on this, we propose a novel neural topic model (NTM) where the representation of words and documents are efficiently and naturally combined into a uniform framework. Extending from NTM, we can easily add a label layer and propose the supervised neural topic model (sNTM) to tackle supervised tasks. Experiments show that our models are competitive in both topic discovery and classification/regression tasks.
UR - http://www.scopus.com/inward/record.url?scp=84959877831&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84959877831&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84959877831
T3 - Proceedings of the National Conference on Artificial Intelligence
SP - 2210
EP - 2216
BT - Proceedings of the 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015
PB - AI Access Foundation
T2 - 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015
Y2 - 25 January 2015 through 30 January 2015
ER -