Open Source Artificial Intelligence Software

Lack of multi-application text corpus despite of the surging text data is a serious bottleneck in the text mining and natural language processing especially in Persian language. This project presents a new corpus for NEWS articles analysis in Persian called Persica. NEWS analysis includes NEWS classification, topic discovery and classification, category classification and many more procedures. Dealing with NEWS has special requirements and first of all a valid and reliable corpus to perform the experiments on them. Please use this reference to cite us: @inproceedings{eghbalzadeh2012persica, title={Persica: A Persian corpus for multi-purpose text mining and Natural language processing}, author={Eghbalzadeh, Hamid and Hosseini, Behrooz and Khadivi, Shahram and Khodabakhsh, Ali}, booktitle={Telecommunications (IST), 2012 Sixth International Symposium on}, pages={1207--1214}, year={2012}, organization={IEEE} }

IT WILL WORK WITH A JAVA DEVELOPMENT KIT 1.7 ONLY !!! This program is a data-miner and a knowledge-miner. It does exactly the opposite of what the text summarizers do. A text summarizer produces a shortened text given some text as an input. An inverse summarizer takes the shortened input, a similar or a same text and does the process in reverse. This results in an expanded text. It can be used with any text or notes that have the knowledge gaps. It is a great aid to any creative work and it simply pin-points to data that may be of some relevance. How to run this program? 1. Make sure JAVA 1.7 development is installed and running/compiling properly with all environment variables properly set. 2. Uncompress the LITE release into a desired directory. 3. Go to a src/ directory with a Terminal/Console/Command-Prompt and do the following: javac Te2.java java Te2 The program should open.