ConText v4.00: C++ program for neural networks for text categorization

ConText v4.00 provides a C++ implementation of neural networks for text categorization described in:

• Deep pyramid convolutional neural networks for text categorization. Rie Johnson and Tong Zhang. ACL 2017.
• Effective use of word order for text categorization with convolutional neural networks. Rie Johnson and Tong Zhang. NAACL HLT 2015.
• Semi-supervised convolutional neural networks for text categorization via region embedding. Rie Johnson and Tong Zhang. NIPS 2015.
• Supervised and semi-supervised text categorization using LSTM for region embeddings. Rie Johnson and Tong Zhang. ICML 2016.

ConText v4.00 is available at http://riejohnson.com/cnn_download.html.

System Requirements: This software runs only on a CUDA-capable GPU such as Tesla K20. That is, your system must have a GPU and an appropriate version of CUDA installed. The provided makefile and example shell scripts are for Unix-like systems. Testing was done on Linux. In principle, the C++ code should compile and run also in other systems (e.g., Windows), but no guarantee. See README for more details.

Download & Documentation: See http://riejohnson.com/cnn_download.html#download.

Getting Started

1. Download the code and extract the files, and read README (not README.md).
2. Go to the top directory and build executables by entering make, after customizing makefile as needed.
   (If you downloaded from GitHub, make also decompresses sample text files that exceed GitHub file size limit and does chmod +x on shell scripts.)
3. To confirm installation, go to examples/ and enter ./sample.sh.
   (See README for installation trouble shooting.)
4. Read Section 1 (Overview) of User Guide to get an idea.
5. Try some shell scripts at examples/. There is a table of the scripts in Section 1.6 of User Guide.

Data Source: The data files were derived from Large Move Review Dataset (IMDB) [MDPHN11] and Amazon reviews [ML13].

Licence: This program is free software issued under the GNU General Public License V3.

References
[MDPHN11] Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng, and Christopher Potts. Learning word vectors for sentiment analysis. ACL 2011.
[ML13] Julian McAuley and Jure Leskovec. Hidden factors and hidden topics: understanding rating dimensions with review text. RecSys 2013.

Note: This GitHub repository provides a snapshot of research code, which is constantly changing elsewhere for research purposes. For this reason, it is very likely that pull requests will be declined.