Курсы машинного перевода для языков России/Session 0 - Revision history

Trondtr: moved Машинный перевод для языков России/Session 0 to Курсы машинного перевода для языков России/Session 0: ... to get a better structure.

2012-01-31T12:00:28Z

moved Машинный перевод для языков России/Session 0 to Курсы машинного перевода для языков России/Session 0: ... to get a better structure.

Francis Tyers: /* Direct */

2012-01-10T23:27:56Z

Direct

Francis Tyers: /* Synthesis */

2012-01-10T21:46:48Z

Synthesis

Francis Tyers: /* Transfer */

2012-01-10T21:44:31Z

Transfer

Francis Tyers: /* Transfer */

2012-01-10T21:44:14Z

Transfer

Francis Tyers: /* Transfer */

2012-01-10T21:42:22Z

Transfer

Francis Tyers: /* Direct */

2012-01-10T12:59:32Z

Direct

Francis Tyers: /* Direct */

2012-01-10T12:38:50Z

Direct

Francis Tyers: /* Transfer */

2012-01-10T08:53:40Z

Transfer

Francis Tyers: /* Directory layout */

2012-01-09T14:58:30Z

Directory layout

@@ Line 23: / Line 23: @@
 [[File:Session0 primer1.svg|center]]
-<!--
-Генрих сетö яй кусöк аслас понлы. :: Heinrich gives piece meat his dog.DAT
-Heinrich antoi lihapalan koiralleen. :: Heinrich gives meat.piece.ACC dog.HIS.TO
--->
 ===Transfer===

@@ Line 59: / Line 59: @@
 This is the problem that in a given language there is usually more than one way to communicate the same meaning for any given meaning.
-:EXEMPLE 4
 :Эсир мӗнле пурӑнатӑр?
 :Мӗнле пурнӑҫсем?
@@ Line 66: / Line 65: @@
 All of these questions demand the same answer (how are you), but they may be more or less frequently used, or emphasise different things.
 In Apertium, for a given input sentence, one output sentence is produced. It is up to the designer of the translation system to choose which translation they want the system to produce. Often we recommend the most literal translation possible, as this reduces the necessity of transfer rules.

@@ Line 32: / Line 32: @@
 Transfer-based machine translation works by first converting the source language to a language-dependent intermediate representation, and then rules are applied to this intermediate representation in order to change the structure of the source language to the structure of the target language. The translation is generated from this representation using both bilingual dictionaries and grammatical rules.
-There can be differences in the level of abstraction of the intermediate representation. We can distinguish two broad groups, shallow transfer, and deep transfer. In shallow-transfer MT the intermediate representation is usually either based on morphology or shallow syntax. In deep-transfer MT the intermediate representation usually includes some kind of parse tree or graph structure (see images on the right).
 [[File:Session0 primer2.svg|300px|right]]
+There can be differences in the level of abstraction of the intermediate representation. We can distinguish two broad groups, shallow transfer, and deep transfer. In shallow-transfer MT the intermediate representation is usually either based on morphology or shallow syntax. In deep-transfer MT the intermediate representation usually includes some kind of parse tree or graph structure (see images on the right).
 Transfer-based MT usually works as follows: The original text is first analysed and disambiguated morphologically (and in the case of deep transfer, syntactically) in order to obtain the source language intermediate representation. The transfer process then converts this final representation (still in the source language) to a representation of the same level of abstraction in the target language. From the target language representation, the target language is generated.

@@ Line 35: / Line 35: @@
 There can be differences in the level of abstraction of the intermediate representation. We can distinguish two broad groups, shallow transfer, and deep transfer. In shallow-transfer MT the intermediate representation is usually either based on morphology or shallow syntax. In deep-transfer MT the intermediate representation usually includes some kind of parse tree or graph structure (see images on the right).
-[[File:Session0 primer2.svg|thumb|right]]
+[[File:Session0 primer2.svg|300px|right]]
 Transfer-based MT usually works as follows: The original text is first analysed and disambiguated morphologically (and in the case of deep transfer, syntactically) in order to obtain the source language intermediate representation. The transfer process then converts this final representation (still in the source language) to a representation of the same level of abstraction in the target language. From the target language representation, the target language is generated.

@@ Line 35: / Line 35: @@
 There can be differences in the level of abstraction of the intermediate representation. We can distinguish two broad groups, shallow transfer, and deep transfer. In shallow-transfer MT the intermediate representation is usually either based on morphology or shallow syntax. In deep-transfer MT the intermediate representation usually includes some kind of parse tree or graph structure (see images on the right).
+[[File:Session0 primer2.svg|thumb|right]]
-:EXEMPLE 2
 Transfer-based MT usually works as follows: The original text is first analysed and disambiguated morphologically (and in the case of deep transfer, syntactically) in order to obtain the source language intermediate representation. The transfer process then converts this final representation (still in the source language) to a representation of the same level of abstraction in the target language. From the target language representation, the target language is generated.
 ===Interlingual===

← Older revision	Revision as of 12:00, 31 January 2012
(No difference)

@@ Line 22: / Line 22: @@
 Direct, or word-for-word machine translation works by reading words in the source language one at a time, and looking them up in a bilingual word list of surface forms. Words may also be deleted, or left out, and maybe translated to one or more words. No grammatical analysis is done, so even simple errors, such as agreement in gender and number between a determiner and head noun will remain in the target language output.
+[[File:Session0 primer1.svg|center]]
-:Heinrich köpeğine bir parça et verir.
-:Генрих хӑйӗн йыттине пӗр татӑк аш парать.
-:Генрих даёт кусок мяса своей собаке.
 <!--
 Генрих сетö яй кусöк аслас понлы. :: Heinrich gives piece meat his dog.DAT

@@ Line 76: / Line 76: @@
 :EXEMPLE 5
+:''Minä pidän uimisesta''
-In Apertium, rules are applied which convert source language structure to target language structure using sequences of lexical forms as an intermediate representation. For further information see: Session 5: Structural transfer basics.
+In Apertium, rules are applied which convert source language structure to target language structure using sequences of lexical forms as an intermediate representation. For further information see: Session 5: Structural transfer basics.
 ===Description===

@@ Line 128: / Line 128: @@
 | <code>apertium-tt-ba.ba.twol</code>  || Phonological rules || Bashkir morphophonological rules || [[Машинный перевод для языков России/Session 1|1]] [[Машинный перевод для языков России/Session 2|2]]
 |-
-| <code>apertium-fr-es.tt.lexc</code>      || Dictionary || Tatar morphotactic dictionary, used for analysis and generation || [[Машинный перевод для языков России/Session 1|1]] [[Машинный перевод для языков России/Session 2|2]]
+| <code>apertium-tt-ba.tt.lexc</code>      || Dictionary || Tatar morphotactic dictionary, used for analysis and generation || [[Машинный перевод для языков России/Session 1|1]] [[Машинный перевод для языков России/Session 2|2]]
 |-
 | <code>apertium-tt-ba.tt.twol</code>  || Phonological rules || Tatar morphophonological rules || [[Машинный перевод для языков России/Session 1|1]] [[Машинный перевод для языков России/Session 2|2]]