Lexical selection in target language - Revision history

Unhammer at 21:06, 1 December 2013

2013-12-01T21:06:55Z

Unhammer at 21:06, 1 December 2013

2013-12-01T21:06:38Z

Bech: Category:Documentation in English

2012-03-24T11:36:46Z

Category:Documentation in English

Francis Tyers at 17:26, 23 January 2009

2009-01-23T17:26:40Z

Francis Tyers at 13:34, 30 October 2008

2008-10-30T13:34:48Z

Francis Tyers at 13:29, 30 October 2008

2008-10-30T13:29:19Z

Francis Tyers at 13:13, 30 October 2008

2008-10-30T13:13:07Z

Francis Tyers at 12:16, 30 October 2008

2008-10-30T12:16:40Z

Francis Tyers at 12:13, 30 October 2008

2008-10-30T12:13:25Z

Francis Tyers at 12:11, 30 October 2008

2008-10-30T12:11:12Z

← Older revision		Revision as of 21:06, 1 December 2013
Line 1:		Line 1:
			:''This module deals with [[lexical selection]], for more information on the topic, see the [[lexical selection\|main page]].''
	{{deprecated}}		{{deprecated}}

@@ Line 1: / Line 1: @@
+{{deprecated}}
 With apertium-multiple-translations it is possible to get an ambiguous text output from transfer, it comes in the following form:
@@ Line 66: / Line 68: @@
 ==See also==
-* [[Lextor]]
+* [[Lexical selection]]
 * [[Word sense disambiguation]]

@@ Line 71: / Line 71: @@
 [[Category:Development]]
 [[Category:Lexical selection]]
+[[Category:Documentation in English]]

← Older revision		Revision as of 17:26, 23 January 2009
Line 70:		Line 70:

	[[Category:Development]]		[[Category:Development]]
			[[Category:Lexical selection]]

@@ Line 63: / Line 63: @@
 A minor improvement, but something that could be improved with more work.
+==See also==
+* [[Lextor]]
+* [[Word sense disambiguation]]
 [[Category:Development]]

@@ Line 3: / Line 3: @@
 :<code>Language is everyone declaring clear be the capacity to get education through the medium Welsh after increase  {constantly|steadily|constant|steady} in the {recent|last} years , and be your government wishing to promote that objective</code>
+Original sentence:
-While this is useful as-is, one of the things we can do with it is try to do a ranking based on a target language model. Each of the options given is kind of ok, but some sound more fluent than others.
+:<code>Mae iaith pawb yn datgan yn glir fod y gallu i gael addysg drwy gyfrwng y Gymraeg wedi cynyddu’n gyson yn y blynyddoedd diwethaf , a bod eich llywodraeth yn dymuno hybu’r amcan hwnnw</code>
+While the multiple-translation output is useful as-is, one of the things we can do with it is try to do a ranking based on a target language model. Each of the options given is kind of ok, but some sound more fluent than others.
 The ambiguous entries come from a target-language polysemia dictionary which looks something like:

@@ Line 46: / Line 46: @@
 </pre>
-At each stage you choose the most likely and construct the final sentence as you go along:
+At each stage you choose the most likely and construct the final sentence as you go along, the final output (for 1--5 grams being):
 :<code>Language is everyone declaring clear be the capacity to get education through the medium Welsh after increase constantly in the last years , and be  your government wishing to  promote  that objective</code>
+and for 2--5 grams:
+:<code>Language is everyone declaring clear be the capacity to get education through the medium Welsh after increase steadily in the last years , and be  your government wishing to  promote  that objective</code>
 Original:

@@ Line 3: / Line 3: @@
 :<code>Language is everyone declaring clear be the capacity to get education through the medium Welsh after increase  {constantly|steadily|constant|steady} in the {recent|last} years , and be your government wishing to promote that objective</code>
-While this is useful as-is, one of the things we can do with it is try to do a ranking based on a target language model. Each of the options given is kind of ok, but some sound more fluent than others. So... first you calculate your ''very basic'' n-gram model, for example of [1-5] grams over a corpus. It might look something like this:
+While this is useful as-is, one of the things we can do with it is try to do a ranking based on a target language model. Each of the options given is kind of ok, but some sound more fluent than others.
+The ambiguous entries come from a target-language polysemia dictionary which looks something like:
+<pre>
+    <e><p><l>constant<s n="adj"/></l><r>constant<s n="adj"/></r></p></e>
+    <e><p><l>constant<s n="adj"/></l><r>constantly<s n="adv"/></r></p></e>
+    <e><p><l>constant<s n="adj"/></l><r>steady<s n="adj"/></r></p></e>
+    <e><p><l>constant<s n="adj"/></l><r>steadily<s n="adv"/></r></p></e>
+    <e><p><l>last<s n="adj"/></l><r>last<s n="adj"/></r></p></e>
+    <e><p><l>last<s n="adj"/></l><r>recent<s n="adj"/></r></p></e>
+</pre>
+This dictionary could be automatically generated from an existing bidix (by taking the restrictions) or from a thesaurus, or manually.
+So... if you want to do target-language based scoring, first you calculate your ''very basic'' n-gram model, for example of [1-5] grams over a corpus. It might look something like this:
 <pre>