Lyapunov filtering of objectivity for Spanish sentiment model

Chaturvedi, Iti, Cambria, Erik, and Vilares, David (2016) Lyapunov filtering of objectivity for Spanish sentiment model. In: Proceedings of the International Joint Conference on Neural Networks. pp. 4474-4481. From: IJCNN: 2016 International Joint Conference on Neural Networks, 24-29 July 2016, Vancouver, Canada.

[img] PDF (Published Vesion) - Published Version
Restricted to Repository staff only

View at Publisher Website: https://doi.org/10.1109/IJCNN.2016.77277...
 
11
1


Abstract

Objective sentences lack sentiments and, hence, can reduce the accuracy of a sentiment classifier. Traditional methods prior to 2001 used hand-crafted templates to identify subjectivity and did not generalize well for resource-deficient languages such as Spanish. Later works published between 2002 and 2009 proposed the use of deep neural networks to automatically learn a dictionary of features (in the form of convolution kernels) that is portable to new languages. Recently, recurrent neural networks are being used to model alternating subjective and objective sentences within a single review. Such networks are difficult to train for a large vocabulary of words due to the problem of vanishing gradients. Hence, in this paper we consider use of a Lyapunov linear matrix inequality to classify Spanish text as subjective or objective by combining Spanish features and features obtained from the corresponding translated English text. The aligned features for each sentence are next evolved using multiple kernel learning. The proposed Lyapunov deep neural network outperforms baselines by over 10% and the features learned in the hidden layers improve our understanding subjective sentences in Spanish.

Item ID: 63352
Item Type: Conference Item (Research - E1)
ISBN: 978-1-5090-0620-5
Copyright Information: © 2016 IEEE.
Date Deposited: 08 Jul 2020 05:16
FoR Codes: 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080107 Natural Language Processing @ 50%
08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080108 Neural, Evolutionary and Fuzzy Computation @ 50%
SEO Codes: 97 EXPANDING KNOWLEDGE > 970108 Expanding Knowledge in the Information and Computing Sciences @ 100%
Downloads: Total: 1
Last 12 Months: 1
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page