| 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 13:13]
kravalova stará verze byla obnovena |
| * 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 |
| | |
| |
| |
| </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> |
| |
| ===== TectoMT Architecture ===== | ===== TectoMT Architecture ===== |
| | |
| |
| |
| |
| * 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''. |
| | |
| |
| |
| 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/''. |
| * Each bundle contains tree shaped sentence representations on various linguistic layers. In our example ''sample.tmt'' we have morphological tree (''SEnglishM'') in each bundle. Later on, also an analytical layer (''SEnglishA'') will appear in each bundle as we proceed with our analysis. | * Each bundle contains tree shaped sentence representations on various linguistic layers. In our example ''sample.tmt'' we have morphological tree (''SEnglishM'') in each bundle. Later on, also an analytical layer (''SEnglishA'') will appear in each bundle as we proceed with our analysis. |
| * Trees are formed by nodes and edges. Attributes can be attached only to nodes. Edge's attributes must be stored as the lower node's attributes. Tree's attributes must be stored as attributes of the root node. | * Trees are formed by nodes and edges. Attributes can be attached only to nodes. Edge's attributes must be stored as the lower node's attributes. Tree's attributes must be stored as attributes of the root node. |
| | |
| | |
| |
| |
| </code> | </code> |
| |
| //Note//: Makefiles use tabulators to mark command lines. Make sure your lines start with tabulator (or two tabulators) and not, for example, with 4 spaces. | //Note//: Makefiles use tabulators to mark command lines. Make sure your lines start with a tabulator (or two tabulators) and not, for example, with 4 spaces. |
| |
| After running | After running |
| //Note//: For more information about tree editor TrEd, see [[http://ufal.mff.cuni.cz/~pajas/tred/ar01-toc.html|TrEd User's Manual]]. | //Note//: For more information about tree editor TrEd, see [[http://ufal.mff.cuni.cz/~pajas/tred/ar01-toc.html|TrEd User's Manual]]. |
| |
| | If you are not familiar with Makefile syntax, another way of running a scenario in TectoMT is using ''.scen'' file (see ''applications/tutorial.scen''). This file lists the blocks to be run - one block on a single line. |
| |
| | <code bash> |
| | eval ${TMT_ROOT}/tools/format_convertors/plaintext_to_tmt/plaintext_to_tmt.pl English sample.txt |
| | brunblocks -S -o --scen tutorial.scen -- sample.tmt |
| | </code> |
| |
| | Finally, yet another way is to use a simple ''bash'' script (see ''applications/run_all.sh''): |
| | |
| | <code bash> |
| | ./run_all.sh |
| | </code> |
| |
| |
| |
| ===== Advanced block: finite clauses ===== | ===== Advanced block: finite clauses ===== |
| | |
| |
| |
| ==== 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. |
| |
| |
| |
| ===== Your turn: more tasks ===== | ===== Your turn: more tasks ===== |
| | |
| | |
| |
| |
| ==== 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. |
| |
| * 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'''. |
| | |
| |
| |
| {{ 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. |
