Home

{{AFC submission|d|v|u=Kamykowsari|ns=118|decliner=Bradv|declinets=20171216044723|ts=20171214162111}} {{Machine learning bar}}

'''Hierarchical Deep Learning for Text Classification (HDLTex)''' is the machine learning task with the "hierarchical labeled" data (a classification or categorization). Since the examples given to the learner are hierarchical labeled, the evaluation is based on the accuracy or F1-measure based on multi level of the model hierarchy. This model have been used for text classification, as in HDLTex: Hierarchical Deep Learning for Text Classification where HDLTex employs stacks of deep learning architectures to provide specialized understanding at each level of the document hierarchy.

Approaches as part of HDLTex include:

• convolution neural network
• recurrent neural network
• Deep neural network

== Hierarchical Deep Learning ==

The primary contribution of this technique is hierarchical classificationKowsari, K., Brown, D. E., Heidarysafa, M., Meimandi, K. J., Gerber, M. S., & Barnes, L. E. (2017). Hdltex: Hierarchical deep learning for text classification. [https://arxiv.org/abs/1709.08267 arXiv preprint arXiv:1709.08267]. of documents. A traditional multi-class classification technique can work well for a limited number classes, but performance drops with increasing number of classes, as is present in hierarchically organized documents. Many techniques works on Hierarchical Attention for text classificationYang, Z., Yang, D., Dyer, C., He, X., Smola, A. J., & Hovy, E. H. (2016). [http://www.aclweb.org/anthology/N16-1174 Hierarchical Attention Networks for Document Classification]. In HLT-NAACL (pp. 1480-1489).. In hierarchical deep learning model, this problem is solved by creating architectures that specialize deep learning approaches for their level of the document hierarchy. The structure of Hierarchical Deep Learning for Text (HDLTex) architecture for each deep learning model is as follows:

• convolution neural network
• recurrent neural network
• Deep neural network File:HDLTex.jpg

== Method of moments == Document classification is an important problem to address, given the growing size of scientific literature and other document sets. When documents are organized hierarchically, multi-class approaches are difficult to apply using traditional supervised learning methods. HDLTex combines multiple deep learning approaches to produce hierarchical classifications. The deep learning methods can provide improvements for document classification and that they provide flexibility to classify documents within a hierarchy. Hence, they provide extensions over current methods for document classification that only consider the multi-class problem. The methods described as HDLTex can improved in multiple ways. Additional training and testing with other hierarchically structured document data sets will continue to identify architectures that work best for these problems. Also, it is possible to extend the hierarchy to more than two levels to capture more of the complexity in the hierarchical classification. For example, if keywords are treated as ordered then the hierarchy continues down multiple levels. HDLTex can also be applied to unlabeled (unsupervised) documents, such as those found in news or other media outlets.

== See also ==

• Deep Learning
• Natural language processing
• Document classification
• classification

== Notes == {{reflist}}

== Further reading ==

• LeCun, Y., Bengio, Y., & Hinton, G. (2015). [https://www.nature.com/articles/nature14539 Deep learning]. Nature, 521(7553), 436-444.
• Deng, Li, and Dong Yu. "[http://ftp.nowpublishers.com/article/Details/SIG-039 Deep learning: methods and applications.]" Foundations and Trends® in Signal Processing 7.3–4 (2014): 197-387. *Schmidhuber, J. (2015). [http://www.sciencedirect.com/science/article/pii/S0893608014002135 Deep learning in neural networks: An overview.] Neural networks, 61, 85-117.
• {{cite book |editor1=Geoffrey Hinton |editor2=Terrence J. Sejnowski |year=1999 |title=Unsupervised Learning: Foundations of Neural Computation |publisher=MIT Press |isbn=0-262-58168-X}} (This book focuses on unsupervised learning in neural networks)

{{DEFAULTSORT:supervised Learning}} :Category:supervised learning :Category:Deep Learning :Category:Machine learning