About - Revision history

Admin at 09:46, 20 December 2018

2018-12-20T09:46:32Z

2018-12-20T09:42:47Z

2018-12-20T09:41:52Z

2018-10-09T10:27:48Z

2018-10-09T10:27:10Z

2018-10-09T10:15:58Z

2018-10-09T10:10:42Z

2018-10-09T10:10:04Z

2018-10-09T10:09:35Z

2018-10-09T10:07:52Z

@@ Line 114: / Line 114: @@
 === This Wiki ===
-We are now building a sample web site based on leading edge technology namely (MediaWiki) and incorporating the intelligence mentioned above using the built in Semantic Capabilities of MediaWiki.
+We are now building a sample web site based on Web 3.0 technology namely (MediaWiki) and incorporating the intelligence mentioned above using the built in Semantic Capabilities of MediaWiki.
 We have also successfully demonstrated and used the multi language capabilities using the built in features of MediaWiki.

@@ Line 31: / Line 31: @@
 === Structure of Concept Tree ===
-[[http://corpus.quran.com/]] an annotated linguistic resource which shows the Arabic grammar, syntax and morphology for each word in the Holy Quran.
+[[http://corpus.quran.com/ corpus.quran.com]] an annotated linguistic resource which shows the Arabic grammar, syntax and morphology for each word in the Holy Quran.
 === Data Mining Tools ===

@@ Line 8: / Line 8: @@
 === Contents ===
 ==== Tanzil Project ====
 Tanzil is a Quranic project launched in early 2007 to produce a highly verified Unicode Quran text to be used in Quranic websites and applications. Our mission in the Tanzil project is to produce a standard Unicode Quran text and serve as a reliable source for this standard text on the web. [http://tanzil.net/docs/Tanzil_Project| Tanzil Project]
@@ Line 31: / Line 30: @@
 The goal of this website is to provide the first online, authentic, searchable, and multilingual (English/Arabic at the individual hadith level) database of collections of hadith from our beloved Prophet Muhammad, peace and blessings be upon him.
+=== Structure of Concept Tree ===
 === Data Mining Tools ===
 ==== [https://en.wikipedia.org/wiki/Data_mining Data Mining] ====

@@ Line 99: / Line 99: @@
 === Dealing with Transliteration and Arabic Names ===
 Some of the challenges that we managed to partially resolve is the inconsistent spelling among translation for the Arabic names or Islamic terms. Islamic Material contains lots of transliteration from the Arabic language.  Translators opt to transliterate in the absence of proper English translation or in cases where they cite Sacred Text like Quran or Hadith.
 We have manually searched for transliteration and replaced it with English translation.  We developed an automated process to identify and translate the Transliteration.  However, the process is not very reliable and we manually checked the material for Transliteration.  The process depends on “Spell Checking” and if a word is flagged as misspelled, then that is in indication of possible transliteration.
 === Content Classification ===

@@ Line 97: / Line 97: @@
-==== Dealing with Transliteration and Arabic Names ====
+=== Dealing with Transliteration and Arabic Names ===
-Some of the challenges that we managed to resolve is the inconsistent spelling among translation for the Arabic names or Islamic terms.
+=== Content Classification ===
 We also managed to device a process where we can automatically classify contents into topics (Content Classification).  I have implemented this process in a section of the contents with very promising results. We have also managed to automatically identify association between topics and structure the topic similarity into (Association Rules).
-Previously we have successfully built an indexing engine to transfer spoken words to written text.  This allows for searching and indexing of media files.  It also subjects media file to the Content Classification process and Association Rules processes.
+=== Voice to Text Engine ===
 We are now building a sample web site based on leading edge technology namely (MediaWiki) and incorporating the intelligence mentioned above using the built in Semantic Capabilities of MediaWiki.
 We have also successfully demonstrated and used the multi language capabilities using the built in features of MediaWiki.

@@ Line 93: / Line 93: @@
 [[File:Spellchk.jpg|1000px|center]] to use the full version of the file
+table showing the Spell Checker Recommendation Utility output. Column 1 “Original Word”, Column 2 “Suggested Word”, Column 3: Original Word “Sound Like”, Column4: “Suggested Word Sound Like”.  Column5: matching column 3 to column 4.  Column 6: Similarity Distance between Original and Suggested Word, column 7: Final Recommendation.
 === Transliteration ===

@@ Line 91: / Line 91: @@
 )	How many operations needs to be performed before the original word can be transferred to the suggested word, commonly known in the field as “Word Distance”.
 )	The Word Similarity.
-[[File:Spellchk.jpg|2000px|center]] to use the full version of the file
+[[File:Spellchk.jpg|1000px|center]] to use the full version of the file
 === Transliteration ===

@@ Line 91: / Line 91: @@
 )	How many operations needs to be performed before the original word can be transferred to the suggested word, commonly known in the field as “Word Distance”.
 )	The Word Similarity.
-[[File:Spellchk.jpg]] to use the full version of the file
+[[File:Spellchk.jpg|200px|center]] to use the full version of the file
 [[File:File.png|200px|thumb|left|alt text]] to use a 200 pixel wide rendition in a box in the left margin with "alt text" as description
 [[Media:File.ogg]] for directly linking to the file without displaying the file