Algorithms 2015, 8(3), 562-572; doi:10.3390/a8030562
Modeling Documents with Event Model
1
Tsinghua University, Beijing 100000, China
2
School of Mechanical Engineering, Shandong University, Jinan 250061, China
*
Author to whom correspondence should be addressed.
Academic Editor: Jun-Bao Li
Received: 3 May 2015 / Accepted: 23 July 2015 / Published: 4 August 2015
Abstract
Currently deep learning has made great breakthroughs in visual and speech processing, mainly because it draws lessons from the hierarchical mode that brain deals with images and speech. In the field of NLP, a topic model is one of the important ways for modeling documents. Topic models are built on a generative model that clearly does not match the way humans write. In this paper, we propose Event Model, which is unsupervised and based on the language processing mechanism of neurolinguistics, to model documents. In Event Model, documents are descriptions of concrete or abstract events seen, heard, or sensed by people and words are objects in the events. Event Model has two stages: word learning and dimensionality reduction. Word learning is to learn semantics of words based on deep learning. Dimensionality reduction is the process that representing a document as a low dimensional vector by a linear mode that is completely different from topic models. Event Model achieves state-of-the-art results on document retrieval tasks. View Full-TextKeywords:
deep learning; neurolinguistics; topic model; Event Model; document retrieval
▼
Figures
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).
Share & Cite This Article
MDPI and ACS Style
Wang, L.; Zhao, G.; Sun, D. Modeling Documents with Event Model. Algorithms 2015, 8, 562-572.
Related Articles
Article Metrics
Comments
[Return to top]
Algorithms
EISSN 1999-4893
Published by MDPI AG, Basel, Switzerland
RSS
E-Mail Table of Contents Alert