Generating word and document matrix representations for document classification
Release time:2020-07-19
Hits:
Indexed by:
Journal Papers
First Author:
Guo, Shun
Correspondence Author:
Guo, S (corresponding author), Dalian Univ Technol, Dept Comp Sci & Technol, Dalian, Peoples R China.
Co-author:
Yao, Nianmin
Date of Publication:
2020-07-01
Journal:
NEURAL COMPUTING & APPLICATIONS
Included Journals:
SCIE
Document Type:
J
Volume:
32
Issue:
14
Page Number:
10087-10108
ISSN No.:
0941-0643
Key Words:
Document-level classification; Word matrix; Document matrix; Subwindows
Abstract:
We present an effective word and document matrix representation architecture based on a linear operation, referred to as doc2matrix, to learn representations for document-level classification. It uses a matrix to present each word or document, which is different from the traditional form of vector representation. Doc2matrix defines proper subwindows as the scale of text. A word matrix and a document matrix are generated by stacking the information of these subwindows. Our document matrix not only contains more fine-grained semantic and syntactic information than the original representation but also introduces abundant two-dimensional features. Experiments conducted on four document-level classification tasks demonstrate that the proposed architecture can generate higher-quality word and document representations and outperform previous models based on linear operations. We can see that compared to different classifiers, a convolutional-based classifier is more suitable for our document matrix. Furthermore, we also demonstrate that the convolution operation can better capture the two-dimensional features of the proposed document matrix by the analysis from both theoretical and experimental perspectives.
Translation or Not:
no
