[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki

[ Back to the navigation ]

You are here: start » external » tectomt » tutorial

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
Next revision Both sides next revision
external:tectomt:tutorial [2009/01/22 11:50]
kravalova 		external:tectomt:tutorial [2009/01/22 12:50]
zabokrtsky
Line 21: Line 21:
   * Your shell is bash   * Your shell is bash
   * You have basic experience with bash and can read basic Perl   * You have basic experience with bash and can read basic Perl
 +
 +
  
  
Line 37: Line 39:
 ==== Installation and setup ==== ==== Installation and setup ====
  
-  * Checkout SVN repository. If you are running this installation in computer lab in Prague, you have to checkout the repository into directory ''/home/BIG'' (because bigger disk quota applies here):+  * Checkout SVN repository. If you are running this installation in computer lab in Prague, you have to checkout the repository into directory ''~/BIG'' (because bigger disk quota applies here):
  
 <code bash> <code bash>
Line 51: Line 53:
 </code> </code>
  
-  * In your ''.bashrc'' file, add line (or source this file every time before experimenting with TectoMT):+  * In your ''.bashrc'' file, add line (or source the specified file every time before experimenting with TectoMT):
  
 <code bash> <code bash>
Line 85: Line 87:
  
 ===== TectoMT Architecture ===== ===== TectoMT Architecture =====
 +
  
  
Line 94: Line 97:
  
   * The basic units are blocks. They serve for some very limited, well defined, and often linguistically interpretable tasks (e.g., tokenization, tagging, parsing). Technically, blocks are Perl classes inherited from ''TectoMT::Block'', each saved in a separate file. The blocks repository is in ''libs/blocks/''.   * The basic units are blocks. They serve for some very limited, well defined, and often linguistically interpretable tasks (e.g., tokenization, tagging, parsing). Technically, blocks are Perl classes inherited from ''TectoMT::Block'', each saved in a separate file. The blocks repository is in ''libs/blocks/''.
-  * To solve a more complex task, selected blocks can be chained into a block sequence, called also a scenario. Technically, scenarios are instances of ''TectoMT::Scenario'' class, but in some situations (e.g. on the command line) it is sufficient to specify the scenario simply by listing block names separated with spaces.+  * To solve a more complex task, selected blocks can be chained into a block sequence, called also a scenario. Technically, scenarios are instances of ''TectoMT::Scenario'' class, but in some situations (e.g. on the command line) it is sufficient to specify the scenario simply by listing block names separated by spaces.
   * The highest unit is called application. Applications correspond to end-to-end tasks, be they real end-user applications (such as machine translation), or 'only' NLP-related experiments. Technically, applications are often implemented as ''Makefiles'', which only glue the components existing in TectoMT. Some demo applications can be found in ''applications''.   * The highest unit is called application. Applications correspond to end-to-end tasks, be they real end-user applications (such as machine translation), or 'only' NLP-related experiments. Technically, applications are often implemented as ''Makefiles'', which only glue the components existing in TectoMT. Some demo applications can be found in ''applications''.
  
 This tutorial itself has its blocks in ''libs/blocks/Tutorial'' and the application in ''applications/tutorial''. This tutorial itself has its blocks in ''libs/blocks/Tutorial'' and the application in ''applications/tutorial''.
 +
  
  
Line 124: Line 128:
 Blocks in block repository ''libs/blocks'' are located in directories indicating their purpose in machine translation. Blocks in block repository ''libs/blocks'' are located in directories indicating their purpose in machine translation.
  
-//Example//: Block adding Czech morphological tags (pos, case, gender, etc.) can be found in ''libs/blocks/SCzechW_to_SCzechM/Simple_tagger.pm''.+//Example//: A block adding Czech morphological tags (pos, case, gender, etc.) can be found in ''libs/blocks/SCzechW_to_SCzechM/Simple_tagger.pm''.
  
 There are also other directories for other purpose blocks, for example blocks which only print out some information go to ''libs/Print''. Our tutorial blocks are in ''libs/blocks/Tutorial/''. There are also other directories for other purpose blocks, for example blocks which only print out some information go to ''libs/Print''. Our tutorial blocks are in ''libs/blocks/Tutorial/''.
Line 332: Line 336:
  
 ===== Advanced block: finite clauses ===== ===== Advanced block: finite clauses =====
 +
  
  
Line 340: Line 345:
 ==== Motivation ==== ==== Motivation ====
  
-It is assumed that finite clauses can be translated independently, which would reduce computational complexity or make parallel translation possible. We could even use hybrid translation - each finite clause could be translated by the most self-confident translation system. In this task, we are going to split the sentence into finite clauses.+It is assumed that finite clauses can be translated independently, which would reduce combinatorial complexity or make parallel translation possible. We could even use hybrid translation - each finite clause could be translated by the most self-confident translation system. In this task, we are going to split the sentence into finite clauses.
  
  
Line 410: Line 415:
  
 ===== Your turn: more tasks ===== ===== Your turn: more tasks =====
 +
 +
  
  
Line 427: Line 434:
 ==== SVO to SOV ==== ==== SVO to SOV ====
  
-**Motivation**: During translation from an SVO based language (e.g. English) to an SOV based language (e.g. Korean) we might need to change the word order from SVO to SOV. +**Motivation**: During translation from an SVO based language (e.g. English) to an SOV based language (e.g. Korean), we might need to change the word order from SVO to SOV. 
  
 **Task**: Change the word order from SVO to SOV. **Task**: Change the word order from SVO to SOV.
Line 434: Line 441:
  
   * You can use block template in ''libs/blocks/BlockTemplate.pm''.    * You can use block template in ''libs/blocks/BlockTemplate.pm''. 
-  * To find an object to a verb, look for objects among effective children of a verb (''$child<nowiki>-></nowiki>get_attr('afun') eq 'Obj' ''). That implies working on analytical layer.+  * To find an object of a verb, look for objects among effective children of a verb (''$child<nowiki>-></nowiki>get_attr('afun') eq 'Obj' ''). That implies working on analytical layer.
   * For debugging, a method returning surface word order of a node is useful: ''$node<nowiki>-></nowiki>get_attr('ord')''. It can be used to print out nodes sorted by attribute ''ord''.   * For debugging, a method returning surface word order of a node is useful: ''$node<nowiki>-></nowiki>get_attr('ord')''. It can be used to print out nodes sorted by attribute ''ord''.
-  * Once you have node ''$object'' and node ''$verb'', use method ''$object<nowiki>-></nowiki>shift_before_node($verb)''. This method takes the whole subtree under node ''$object'' and re-counts the attributes ''ord'' (surface word order) so that all nodes in subtree under ''$object'' have smaller ''ord'' than ''$verb''. That is, the method rearranges the surface word order from VO to OV.+  * Once you have the node ''$object'' and the node ''$verb'', use the method ''$object<nowiki>-></nowiki>shift_before_node($verb)''. This method takes the whole subtree under the node ''$object'' and recalculates the attributes ''ord'' (surface word order) so that all the nodes in the subtree under ''$object'' have a smaller ''ord'' than ''$verb''. That is, the method rearranges the surface word order from VO to OV.
  
 **Advanced version**: This solution shifts object (or more objects) of a verb just in front of that verb node. So f.e.: //Mr. Brown has urged MPs.// changes to: //Mr. Brown has MPs urged.// You can try to change this solution, so the final sentence would be: //Mr. Brown MPs has urged.// You may need a method ''$node->shift_after_subtree($root_of_that_subtree)''. Subjects should have attribute '''afun' eq 'Sb'''. **Advanced version**: This solution shifts object (or more objects) of a verb just in front of that verb node. So f.e.: //Mr. Brown has urged MPs.// changes to: //Mr. Brown has MPs urged.// You can try to change this solution, so the final sentence would be: //Mr. Brown MPs has urged.// You may need a method ''$node->shift_after_subtree($root_of_that_subtree)''. Subjects should have attribute '''afun' eq 'Sb'''.
 +
  
  
Line 477: Line 485:
 {{ external:tectomt:preps.png?200x80|Prepositions example}} {{ external:tectomt:preps.png?200x80|Prepositions example}}
  
-**Motivation**: In dependency approach a question "where to hang prepositions" arises. In praguian style (PDT), prepositions are heads of the subtree and the noun/pronoun is dependent on the preposition. However, another ordering might be preferable: The noun/pronoun might be the head of subtree, while the preposition would take the role of a modifier.+**Motivation**: In dependency approach the question "where to hang prepositions" arises. In the praguian style (PDT), prepositions are heads of the subtree and the noun/pronoun is dependent on the preposition. However, another ordering might be preferable: The noun/pronoun might be the head of subtree, while the preposition would take the role of a modifier.
  
 **Task**: The task is to rehang all prepositions as indicated at the picture. You may assume that prepositions have at most 1 child. **Task**: The task is to rehang all prepositions as indicated at the picture. You may assume that prepositions have at most 1 child.

[ Back to the navigation ] [ Back to the content ]