[ESW Wiki] Update of "its0908LinguisticMarkup" by GoutamSaha from w3t-archive+esw-wiki@w3.org on 2005-09-14 (public-i18n-its@w3.org from July to September 2005)

From: <w3t-archive+esw-wiki@w3.org>
Date: Wed, 14 Sep 2005 03:30:54 -0000
To: w3t-archive+esw-wiki@w3.org
Message-ID: <20050914033054.7125.42372@localhost.localdomain>
Dear Wiki user,

You have subscribed to a wiki page or wiki category on "ESW Wiki" for change notification.

The following page has been changed by GoutamSaha:
http://esw.w3.org/topic/its0908LinguisticMarkup


------------------------------------------------------------------------------
     3-Tier Schemas to embed linguistic-related metadata information
     in the structure of an XML document in order to improve the 
     translation process for obtaining more meaningful translation.
+    This 3-tier schema scheme is also useful for the Translation Memory
+    processes to keep context markups when I18N & L10N developers 
+    use this scheme for both source and target text.     
   
     - Develop the 1st xml schema that contains various categories on
       content domain,
@@ -50, +53 @@

   - Examples on word POS categories: for Noun type- proper, 
     abstract,compound etc, and so on.
  
-    Developers can categorize the linguistic-related metadata information in the following ways.
+ Developers can categorize the linguistic-related metadata information in the following ways.
     Metadata information may vary little from one language to another language.
     
     Content Domain
@@ -266, +269 @@

    <right_parenthesis>
    <mid_sentence>
    <other_punctuation>
- ==============================================
+ 
+ ================
+ 
  A typical schema of the content_domain is shown below.
  
  <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
@@ -353, +358 @@

        </xs:complexType>
     </xs:element>
  </xs:schema>
- ==================================
+ 
+ ==================
+ 
  A typical schema for Sentence_categories is shown below.
  
  <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
@@ -427, +434 @@

       </xs:complexType>
    </xs:element>
  </xs:schema>
+ 
- ================
+ ==============
  
+ A typical schema for Parts-of-Speech (POS) Markups is shown below.
+ 
+ <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+ <xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" targetNamespace="http://www.kolkatacdac.in/w3ci18npos" elementFormDefault="qualified">
+ <xs:element name="cat">
+ <xs:complexType mixed="true">
+  <xs:attribute name="name" use="required">
+   <xs:simpleType>
+    <xs:restriction base="xs:string">
+     <xs:enumeration value="adjective"/>
+     <xs:enumeration value="adverb"/>
+     <xs:enumeration value="conjunction"/>
+     <xs:enumeration value="noun"/>
+     <xs:enumeration value="post_position"/>
+     <xs:enumeration value="preposition"/>
+     <xs:enumeration value="pronoun"/>
+     <xs:enumeration value="punctuation"/>
+     <xs:enumeration value="verb"/>
+    </xs:restriction>
+   </xs:simpleType>
+  </xs:attribute>
+  <xs:attribute name="type">
+   <xs:simpleType>
+    <xs:restriction base="xs:string">
+     <xs:enumeration value="abstarct_concrete"/>
+     <xs:enumeration value="abstract"/>
+     <xs:enumeration value="addressing"/>
+      <xs:enumeration value="adjective_adjective"/>
+     <xs:enumeration value="adjective_adverb"/>
+    <xs:enumeration value="adversative_coordinating"/>
+     <xs:enumeration value="cardinals"/>
+     <xs:enumeration value="case"/>
+     <xs:enumeration value="causative"/>
+     <xs:enumeration value="collective"/>
+     <xs:enumeration value="comma"/>
+     <xs:enumeration value="common"/>
+     <xs:enumeration value="comparative"/>
+     <xs:enumeration value="compound"/>
+     <xs:enumeration value="conclusive"/>
+     <xs:enumeration value="coordinating"/>
+     <xs:enumeration value="correlative"/>
+     <xs:enumeration value="demonstrative"/>
+     <xs:enumeration value="denoting_others"/>
+     <xs:enumeration value="disjunctive"/>
+     <xs:enumeration value="end_inflecting"/>
+     <xs:enumeration value="eternal_joined"/>
+     <xs:enumeration value="exclusion"/>
+    <xs:enumeration value="following_noun_of_title"/>
+     <xs:enumeration value="fractional_number"/>
+     <xs:enumeration value="general"/>
+     <xs:enumeration value="group"/>
+     <xs:enumeration value="hyphenated_numbers"/>
+     <xs:enumeration value="imperative"/>
+     <xs:enumeration value="inclusive"/>
+     <xs:enumeration value="indeclinable"/>
+     <xs:enumeration value="indefinite"/>
+     <xs:enumeration value="interjectory"/>
+     <xs:enumeration value="interrogative"/>
+     <xs:enumeration value="intransitive"/>
+     <xs:enumeration value="joining"/>
+     <xs:enumeration value="left_parenthesis"/>
+     <xs:enumeration value="material"/>
+     <xs:enumeration value="mid_sentence"/>
+     <xs:enumeration value="negative"/>
+     <xs:enumeration value="non_finite"/>
+     <xs:enumeration value="noun"/>
+     <xs:enumeration value="noun_location"/>
+     <xs:enumeration value="numbers"/>
+     <xs:enumeration value="numeral"/>
+     <xs:enumeration value="onomatopoeic"/>
+     <xs:enumeration value="ordinal"/>
+     <xs:enumeration value="ordinal_number"/>
+     <xs:enumeration value="other"/>
+    <xs:enumeration value="participle/principal"/>
+     <xs:enumeration value="personal"/>
+     <xs:enumeration value="place"/>
+    <xs:enumeration value="preceeding_noun_of_title"/>
+    <xs:enumeration value="preceeding_noun_title"/>
+    <xs:enumeration value="primary/root"/>
+     <xs:enumeration value="pronoun's"/>
+     <xs:enumeration value="pronounian"/>
+     <xs:enumeration value="proper"/>
+     <xs:enumeration value="quantitative"/>
+     <xs:enumeration value="quote"/>
+     <xs:enumeration value="reflexive"/>
+     <xs:enumeration value="relative"/>
+    <xs:enumeration value="repeated_verb_ending"/>
+     <xs:enumeration value="repetitive"/>
+     <xs:enumeration value="right_parenthesis"/>
+     <xs:enumeration value="sentence_final"/>
+     <xs:enumeration value="subordinating"/>
+     <xs:enumeration value="superlative"/>
+     <xs:enumeration value="suspicion"/>
+     <xs:enumeration value="tense"/>
+     <xs:enumeration value="time"/>
+     <xs:enumeration value="transitive"/>
+    <xs:enumeration value="unit_of_measurement"/>
+     <xs:enumeration value="verb_ending"/>
+     <xs:enumeration value="verbal"/>
+    </xs:restriction>
+   </xs:simpleType>
+  </xs:attribute>
+ </xs:complexType>
+ </xs:element>
+ </xs:schema>
+ 
+ <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+ <xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:p="http://www.kolkatacdac.in/w3ci18npos" 
+ elementFormDefault="qualified">
+ <xs:import namespace="http://www.kolkatacdac.in/w3ci18npos" 
+ schemaLocation="C:\Documents and Settings\Administrator\My Documents\ITS-XML-Test\auth-postag-14091.xsd"/>
+ <xs:element name="pos_tag">
+  <xs:complexType>
+   <xs:sequence>
+    <xs:element ref="p:cat" maxOccurs="unbounded"/>
+   </xs:sequence>
+  </xs:complexType>
+ </xs:element>
+ </xs:schema>
+ 
+ ====================================
+
Received on Wednesday, 14 September 2005 09:51:50 UTC