إذا كنت تستخدم الذخيرة النصية الفصحى في بحثك

آمل أن تخبرنا عن ذلك في الرابط التالي

http://ksucorpus.ksu.edu.sa/ar/?p=91

Advertisements
Posted in Personal | Leave a comment

If you are using KSUCCA in your research ..

Please tell us about it in the following link:

http://ksucorpus.ksu.edu.sa/?p=156

Posted in Personal | Leave a comment

KSUCCA is now available on Sketch Engine

Now you can use Sketch Engine (SkE) to search an annotated version of KSUCCA.

SkE offers a wide range of interesting functionality, and you can try it freely for 30 days.

Please feel free to provide your comments when you use it.

http://www.sketchengine.co.uk/

Posted in Distributional Lexical semantics, KSUCCA, My Progress, Quranic Arabic Computing, Traditional Arabic Corpus | Leave a comment

Yesterday I had a meeting with Dr. Nawal Alhelwa

Yesterday I had a meeting in Prince Salman Public Library with Dr. Nawal Alhelwa and Mrs Lamia Alaqeel who is doing a PhD on extracting collocations from Almutanabi poems collections . We discussed various aspects regarding Arabic collocations from a linguistic point of view.

Posted in Classical Arabic Corpus, Meetings, My Progress, Traditional Arabic Corpus | 2 Comments

A paper on KSUCCA

We’ve presented a paper on KSUCCA on the Second Workshop on Arabic Corpus Linguistics (WACL-2), a workshop in conjunction with the Corpus Linguistics 2013 conference. You can use it to reference KSUCCA in your work:
Maha Alrabiah, AbdulMalik Al-Salman and Eric Atwell, “The design and construction of the 50 million words KSUCCA King Saud University Corpus of Classical Arabic”, In Second Workshop on Arabic Corpus Linguistics (WACL-2), Monday 22nd July 2013, Lancaster University, UK.
Posted in Classical Arabic Corpus, Distributional Lexical semantics, KSUCCA, My Progress, Quranic Arabic Computing, Traditional Arabic Corpus | Leave a comment

A great free tool for processing Arabic corpora

Dr. Abdulmohsen Althubaity and his research team at King Abdulaziz City for Science and Technology KACST finally published their Arabic ؤorpora processing tool called Alghawas, Diver in English.

You can download it together with the user manual from Sourceforge:

http://sourceforge.net/projects/kacst-acptool/files?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+sourceforge%2Fexport%2Frss_sfnewsreleases+%28Sourceforge%3A+New+Releases%29

The tool is not just a concordance; it has many good features such as frequency lists generation and collocation extraction. In addition, it has been tested on English and French as well. However, the interface of the tool together with the user manual are written in Arabic. Hopefully, they will provide an English version soon.

Posted in Classical Arabic Corpus, Distributional Lexical semantics, KSUCCA, Quranic Arabic Computing, Traditional Arabic Corpus | Leave a comment

Progress so far

I have finished studying the following DSMs in details:

Geometric DSMs:

1- Wordspace by Schutze et al.

2- HAL by Lund & Burgess.

3- LSA by Deerwester.

4-Compositional Expectation by Washtell.

Probabilistic DSMs based on:

1- Frequency.

2- Mean & variance.

3- Hypothesis testing:

3.1- T test.

3.2- Hypothesis testing of difference using T test.

3.3- Pearson’s Chi-square test.

3.4- Likelihood ratios.

3.5- Z-score.

3.6- Fisher’s exact test.

3.7- Good-Turing test.

3.8- Simple Good-Turing test.

4- Mutual Information.

I relied on the following book for the statistical background:

http://www.amazon.com/Probability-Statistics-Engineers-Scientists-Edition/dp/0130415294/ref=sr_1_15?ie=UTF8&qid=1364050104&sr=8-15&keywords=statistics+for+scientist+and+engineers

 

Posted in My Progress | Leave a comment