Abstract
In recent years, learning word vector representations has attracted much interest in Natural Language Processing. Word representations or embeddings learned using unsupervised methods help addressing the problem of traditional bag-of-word approaches which fail to capture contextual semantics. In this paper we go beyond the vector representations at the word level and propose a novel framework that learns higher-level feature representations of n-grams, phrases and sentences using a deep neural network built from stacked Convolutional Restricted Boltzmann Machines (CRBMs). These representations have been shown to map syntactically and semantically related n-grams to closeby locations in the hidden feature space. We have experimented to additionally incorporate these higher-level features into supervised classifier training for two sentiment analysis tasks: subjectivity classification and sentiment classification. Our results have demonstrated the success of our proposed framework with 4% improvement in accuracy observed for subjectivity classification and improved the results achieved for sentiment classification over models trained without our higher level features.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Collobert, R., Weston, J.: A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning. In: ICML (2008)
Dahl, G.E., Adams, R.P., Larochelle, H.: Training Restricted Boltzmann Machines on Word Observations. In: ICML (2012)
Kalchbrenner, N., Grefenstette, E., Blunsom, P.: A convolutional Neural Network for Modelling Sentences. In: ACL (2014)
Lee, H., Grosse, R., Ranganath, R., Ng, A.Y.: Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations. In: ICML (2009)
Lin, C., He, Y., Everson, R.: Sentence Subjectivity Detection with Weakly-Supervised Learning. In: IJCNLP (2011)
Mikolov, T., Zweig, G.: Context Dependent Recurrent Neural Networkl Language Model. Tech. rep., Microsoft Research Technical Report (2012)
Nakagawa, T., Inui, K., Kurohashi, S.: Dependency Tree-based Sentiment Classification using CRFs with Hidden Variables. In: NAACL (2010)
Pang, B., Lee, L.: Opinion Mining and Sentiment Analysis. Foundations and Trends in Information Retrieval 2(12), 1–135 (2008)
Socher, R., Pennington, J., Huang, E.H., Ng, A.Y., Manning, C.D.: Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions. In: EMNLP (2011)
Wiebe, J., Riloff, E.: Creating Subjective and Objective Sentence Classifiers from Unannotated Texts. In: Gelbukh, A. (ed.) CICLing 2005. LNCS, vol. 3406, pp. 486–497. Springer, Heidelberg (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Huynh, T., He, Y., Rüger, S. (2015). Learning Higher-Level Features with Convolutional Restricted Boltzmann Machines for Sentiment Analysis. In: Hanbury, A., Kazai, G., Rauber, A., Fuhr, N. (eds) Advances in Information Retrieval. ECIR 2015. Lecture Notes in Computer Science, vol 9022. Springer, Cham. https://doi.org/10.1007/978-3-319-16354-3_49
Download citation
DOI: https://doi.org/10.1007/978-3-319-16354-3_49
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16353-6
Online ISBN: 978-3-319-16354-3
eBook Packages: Computer ScienceComputer Science (R0)