Learning higher-level features with convolutional restricted Boltzmann machines for sentiment analysis

Huynh, Trung; He, Yulan and Rüger, Stefan (2015). Learning higher-level features with convolutional restricted Boltzmann machines for sentiment analysis. In: Advances in Information Retrieval (Hanbury, Allan; Kazai, Gabriella; Rauber, Andreas and Fuhr, Norbert eds.), Lecture Notes in Computer Science, Springer International Publishing, pp. 447–452.

DOI: https://doi.org/10.1007/978-3-319-16354-3_49

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.

Viewing alternatives

Look up in Google Scholar

Metrics

Public Attention

Altmetrics from Altmetric

Number of Citations

Citations from Dimensions

Item Actions

Export

About

CORE (COnnecting REpositories)

Recommendations