Lexical selection - Revision history

Unhammer: remove links to deprecated stuff

2015-04-29T08:36:46Z

remove links to deprecated stuff

Unhammer: /* Current lexical selection module (2012–current) */

2015-04-29T08:36:08Z

Current lexical selection module (2012–current)

Unhammer at 08:21, 29 April 2015

2015-04-29T08:21:28Z

Unhammer: /* Current lexical selection module (2012–current) */

2015-03-10T08:43:03Z

Current lexical selection module (2012–current)

Bech: Link to French page

2014-10-08T07:13:07Z

Link to French page

Unhammer: /* Current lexical selection module (2012–current) */

2013-12-01T21:09:53Z

Current lexical selection module (2012–current)

Unhammer: /* Current lexical selection module (2012) */

2013-09-23T07:47:58Z

Current lexical selection module (2012)

Jacob Nordfalk at 22:50, 7 September 2012

2012-09-07T22:50:32Z

Jacob Nordfalk at 22:48, 7 September 2012

2012-09-07T22:48:21Z

Unhammer: /* Current lexical selection module (2012) */

2012-09-07T10:20:01Z

Current lexical selection module (2012)

@@ Line 75: / Line 75: @@
 [[Lextor]] works using statistics and requires 1) slightly pre-processed dictionaries and 2) corpora to train the module. '''The module is turned off in most cases as it does not provide an improvement over the baseline.'''
-== See also ==
-* [[Limited rule-based lexical selection]]
-* [[Generating lexical-selection rules]]
-* [[Lexical selection in target language]]

@@ Line 12: / Line 12: @@
 == Current lexical selection module (2012–current) ==
-This is made by [[User:Francis Tyers|Francis Tyers]] and is deployed in the apertium-sh-mk and apertium-kaz-tat language pairs where you can see an example.
+The [[Constraint-based lexical selection module]] / apertium-lex-tools is made by [[User:Francis Tyers|Francis Tyers]] and is deployed in the apertium-sh-mk and apertium-kaz-tat language pairs where you can see an example.
 This uses a module which runs ''after'' bidix, where the bidix output is ambiguous:
@@ Line 25: / Line 25: @@
 * [[How to get started with lexical selection rules]]
 ** [[Как начать работу с правилами по выбору лексики]]
 == Old and alternative approaches ==

@@ Line 23: / Line 23: @@
 * [[Rule-based lexical selection module]]
 * [[Learning rules from parallel and non-parallel corpora]]
-** old page: [[Generating lexical-selection rules from a parallel corpus]]
 * [[How to get started with lexical selection rules]]
 ** [[Как начать работу с правилами по выбору лексики]]
-== The slr/srl approach (2010-2012)  ==
+== Old and alternative approaches ==
-Used in [[apertium-sme-nob]].
+=== The slr/srl + CG approach (2010-2012)  ===
+This was used in [[apertium-sme-nob]] until lately.
 This uses a special [[Constraint Grammar]] (CG) file which runs ''after'' regular morphological disambiguation, but ''before'' bidix:
@@ Line 56: / Line 58: @@
 ** On the other hand side, lexical selection can most often be seen as a / default - special case / dichotomy. A good mode of work is to introduce each rule set with the number array, e.g.: # leat 0 = være, 1 = ha, 2 = måtte («ha å»)
+apertium-sme-nob in 2014 switched to bidix before lex.sel (like the lrx-proc method), but still uses vislcg3 rules instead of lrx-proc.
-== Transfer rule approach (2009)  ==
+=== Transfer rule approach (2009)  ===
 You can make transfer rules that does lexical selection.
@@ Line 66: / Line 70: @@
 * must write rules
-This is the method used in most pairs.
+This is the method used in most trunk pairs.
-== Deprecated (2007) ==
+=== Lextor (2007) ===
-* [[Lextor]] – works using statistics and requires 1) slightly pre-processed dictionaries and 2) corpora to train the module. '''The module is turned off in most cases as it does not provide an improvement over the baseline.'''
+[[Lextor]] works using statistics and requires 1) slightly pre-processed dictionaries and 2) corpora to train the module. '''The module is turned off in most cases as it does not provide an improvement over the baseline.'''
 == See also ==

@@ Line 22: / Line 22: @@
 Some documentation:
 * [[Rule-based lexical selection module]]
-* [[Generating lexical-selection rules from a parallel corpus]]
+* [[Learning rules from parallel and non-parallel corpora]]
+** old page: [[Generating lexical-selection rules from a parallel corpus]]
 * [[How to get started with lexical selection rules]]
 ** [[Как начать работу с правилами по выбору лексики]]

@@ Line 1: / Line 1: @@
+[[Sélection lexicale|En français]]
 {{TOCD}}
 '''Lexical selection''' is the task of choosing, given several source-language (SL) translations with the same part-of-speech (POS), the most adequate translation among them in the target language (TL). The task is related to the task of [[word-sense disambiguation]]. The difference is that its aim is to find the most adequate translation, not the most adequate sense. Thus, it is not necessary to choose between a series of fine-grained senses if all these senses result in the same final translation.

@@ Line 8: / Line 8: @@
 * [[Word sense disambiguation]]
-== Current lexical selection module (2012) ==
+== Current lexical selection module (2012–current) ==
 This is made by [[User:Francis Tyers|Francis Tyers]] an is deployed in XX-XX language pair where you can see an example.

@@ Line 16: / Line 16: @@
 morf.analysis | morf.disambiguation | bidix | lexical selection | structural transfer | morf. generation
 </pre>
-In a sense, it disambiguates the bidix output.
+In a sense, it disambiguates the bidix output (in exactly the same way that morf.disambiguation disambiguates the morf.analysis output).