Arabic Text Summarization

Two approaches for the automatic Arabic text summarization model

are presented and discussed . The two approaches have been evaluated using about

three evaluation techniques and merging two of them to compare the performance of

the two approaches .

The first approach was K-Means Clustering which gave a higher score using BLEU

score in the evaluation calculating with 98.0 % .

The second approach was the TextRank algorithm which gave a higher score using

ROUGE matrix in the evaluation calculating with 70 % .

We used the F1 measure to combine the BLEU and ROUGE and then used it for

evaluating the performance of the two approaches . In this technique , the TextRank

gave a higher score than the K-Means cluster .