Rule-Based Turkish Text Summarizer (RB-TTS)

Abstract

The volume of data produced has exponentially increased with the digital revolution and it continues to race to the limits of the capacity of our computers and supercomputers. Automatic text summarization is one of efforts to tame the bestial product of our daily data production, which have generated the 90 percent of the data ever produced by humans, in the last two years. In order to understand what a text is about, a summary is needed which is short enough not to compromise the understandability, and comprehensive to include the most important topics of that text. Numerous automatic text summarization software which aimed at achieving this goal use semantic relations, thesauri, and word frequency lists. In this paper, development phases and evaluation results of a software tool called Rule Based Turkish Text Summarizer (RB-TTS) are presented. The average success rate of the RB-TTS is analyzed both quantitatively using ROUGE-N metrics and qualitatively. In the qualitative analysis, five summaries, obtained automatically from texts, are evaluated by 10 Ph.D. students from Dokuz Eylul University Department of Linguistics. The summaries generated by RB-TTS software are compared with the summaries, which were written by the authors of the corresponding texts, and marked as close to them.

Keywords

• data processing
• dictionaries. morphology
• natural language processing
• text processing