Matxin 1.0 New Language Pair HOWTO - Revision history

Francis Tyers: Francis Tyers moved page Matxin New Language Pair HOWTO to Matxin 1.0 New Language Pair HOWTO

2016-05-11T13:05:36Z

Francis Tyers moved page Matxin New Language Pair HOWTO to Matxin 1.0 New Language Pair HOWTO

Bech: Link to French page

2014-10-08T07:13:17Z

Link to French page

Bech: direct link

2012-11-11T00:23:19Z

direct link

Bech: Documentation in English

2011-09-03T18:35:04Z

Documentation in English

Francis Tyers: /* Analysis with lttoolbox, apertium-tagger and Constraint Grammar */

2009-12-10T09:04:46Z

Analysis with lttoolbox, apertium-tagger and Constraint Grammar

Unhammer: /* Getting started */

2009-12-09T10:01:16Z

Getting started

Unhammer: /* Analysis */

2009-12-09T09:55:06Z

Analysis

Unhammer at 09:52, 9 December 2009

2009-12-09T09:52:46Z

Unhammer: /* Prerequisites */

2009-12-09T09:51:45Z

Prerequisites

Francis Tyers: /* Intra-chunk */

2009-07-17T16:24:31Z

Intra-chunk

@@ Line 1: / Line 1: @@
+[[Création d'une nouvelle paire avec Matxin|En français]]
 {{TOCD}}
 This page intends to give a step-by-step walk-through of how to create a new translator in the [[Matxin]] platform.

@@ Line 12: / Line 12: @@
 And either:
-* [[Freeling]] (from SVN) and the <code>fl-*</code> tools for Freeling (for the moment these can be found in <code>apertium-tools/freeling</code> in [[SVN|apertium SVN]]), if you're planning on using FreeLing for the analysis/tagging/dependency steps
+* [[Freeling]] (from SVN) and the <code>fl-*</code> tools for Freeling (for the moment these can be found in <code>apertium-tools/freeling</code> in [[Using SVN|apertium SVN]]), if you're planning on using FreeLing for the analysis/tagging/dependency steps
 or
-* [[vislcg3]] (from SVN), if you're planning on using lttoolbox/apertium-tagger and [[Constraint Grammar]] for the analysis/tagging/dependency steps
+* [[Apertium and Constraint Grammar|vislcg3]] (from SVN), if you're planning on using lttoolbox/apertium-tagger and [[Constraint Grammar]] for the analysis/tagging/dependency steps
 ==Overview==
@@ Line 52: / Line 52: @@
 ===Morphological===
-In order to create your morphological analyser in Freeling you basically need to make a full-form list. If there is already an Apertium dictionary for the language, you can use the scripts in [[SVN|apertium SVN]] (module <code>apertium-tools/freeling</code>) to generate a dictionary from scratch, if not, then either build it from scratch, or build a dictionary in [[lttoolbox]] and then generate the list.
+In order to create your morphological analyser in Freeling you basically need to make a full-form list. If there is already an Apertium dictionary for the language, you can use the scripts in [[Using SVN|apertium SVN]] (module <code>apertium-tools/freeling</code>) to generate a dictionary from scratch, if not, then either build it from scratch, or build a dictionary in [[lttoolbox]] and then generate the list.
 For the purposes of this exercise, you can just key in a small dictionary manually. We'll call the dictionary <code>matxin-br-en.br.dicc</code>, and it will contain
@@ Line 410: / Line 410: @@
 ====Noun semantic dictionary====
-The noun semantic dictionary is a simple file which allows basic semantic tagging of lemmas. The works somewhat like lists in Apertium transfer files, and allows the categorisation of nouns into semantic classes, for example ''language'', ''animacy'', ''material'', ''communication medium'' etc. The file is a tab separated list of lemma and semantic tag, for example for our phrase we might want to tag ''brezhoneg'' 'Breton' as <code>[HZK]</code> (an abbreviation of ''hizkuntzak'' 'languages').
+The noun semantic dictionary is a simple file which allows basic semantic tagging of lemmas. They works somewhat like lists in Apertium transfer files, and allows the categorisation of nouns into semantic classes, for example ''language'', ''animacy'', ''material'', ''communication medium'' etc. The file is a tab separated list of lemma and semantic tag, for example for our phrase we might want to tag ''brezhoneg'' 'Breton' as <code>[HZK]</code> (an abbreviation of ''hizkuntzak'' 'languages').
 So make the file <code>matxin-br-en.br.sem_info</code> with the following contents:

@@ Line 541: / Line 541: @@
 As Breton and English differ in the internal structure of noun phrases, the next thing we want to do is transfer the Breton structure into English, this will involve changing {{sc|det nom adj}} to {{sc|det adj nom}}. Another intra-chunk process we want to take care of is the removal of the definite article before a noun which has the semantic tag for language (<code>[HZK+]</code>).
 [[Category:Matxin]]
 [[Category:Documentation]]
 [[Category:HOWTO]]
+[[Category:Documentation in English]]

@@ Line 39: / Line 39: @@
 Typically the choice will rest on what resources you have available, and the strengths and weaknesses of each of these tools.
-==Analysis with lttoolbox, apertium-tagger and Constraint Grammar==
+==Analysis with Apertium and Constraint Grammar==
 (to be written...)
 ==Analysis with FreeLing==

@@ Line 31: / Line 31: @@
 This HOWTO expects the user to have a basic familiarity with the Apertium platform, if you don't, feel free to have a look over the pages: [[lttoolbox]], [[bilingual dictionary]] and [[Apertium New Language Pair HOWTO]].
+For the analysis/disambiguation/dependency steps, there are two main options open:
+# use the Apertium tool [[lttoolbox]] for morphological disambiguation, [[Constraint Grammar]] for rule-based disambiguation and syntactic tagging, [[apertium-tagger]] for statistical disambiguation and finally Constraint Grammar for dependency analysis
+# use [[FreeLing]] for all these steps
+Typically the choice will rest on what resources you have available, and the strengths and weaknesses of each of these tools.
 ==Analysis with lttoolbox, apertium-tagger and Constraint Grammar==

← Older revision	Revision as of 13:05, 11 May 2016
(No difference)

@@ Line 7: / Line 7: @@
 This page does not give instructions on installing [[Matxin]], but presumes that the following packages are correctly installed.
 * [[lttoolbox]] (from SVN)
-* [[Freeling]] (from SVN)
 * [[Matxin]] (from SVN)
 * a text editor
-* The <code>fl-*</code> tools for Freeling (for the moment these can be found in <code>apertium-tools/freeling</code> in [[SVN|apertium SVN]])
+And either:
+* [[Freeling]] (from SVN) and the <code>fl-*</code> tools for Freeling (for the moment these can be found in <code>apertium-tools/freeling</code> in [[SVN|apertium SVN]]), if you're planning on using FreeLing for the analysis/tagging/dependency steps
+or
+* [[vislcg3]] (from SVN), if you're planning on using lttoolbox/apertium-tagger and [[Constraint Grammar]] for the analysis/tagging/dependency steps
 ==Overview==

← Older revision		Revision as of 16:24, 17 July 2009
Line 528:		Line 528:

	As Breton and English differ in the internal structure of noun phrases, the next thing we want to do is transfer the Breton structure into English, this will involve changing {{sc\|det nom adj}} to {{sc\|det adj nom}}. Another intra-chunk process we want to take care of is the removal of the definite article before a noun which has the semantic tag for language (<code>[HZK+]</code>).		As Breton and English differ in the internal structure of noun phrases, the next thing we want to do is transfer the Breton structure into English, this will involve changing {{sc\|det nom adj}} to {{sc\|det adj nom}}. Another intra-chunk process we want to take care of is the removal of the definite article before a noun which has the semantic tag for language (<code>[HZK+]</code>).