Corpus based preposition selection - HOWTO

From Apertium
Revision as of 13:15, 23 August 2012 by Fpetkovski (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

The general algorithm for performing corpus based preposition selection is as follows:

  • Download a parallel corpus
  • Extract patterns which contain prepositions from the source-language corpus
  • Align the patterns to their translations in the target-language corpus
  • Extract the features and corresponding labels (the correct preposition from the target-language corpus) for classification.
  • Train a model
  • Use the trained model in the translation pipeline

The general toolkit for performing these tasks can be found here.

The toolkit[edit]

Preposition Extraction[edit]

The tool for preposition extraction takes a stream in the format ^lemma<tags>$ ^lemma<tags>$ on standard input and outputs a list of extracted patterns which are later used in the alignment process. The program will match patterns in the form of: (n|vblex) (pr) (adj | det)* (n|vblex)


echo "^Косово<np><top><nt><sg><nom>$ ^испитува<vblex><imperf><tv><pres><p3><sg>$ ^процес<n><m><sg><nom><def>$ ^на<pr>$ ^приватизација<n><f><sg><nom><ind><@P←>$^.<sent>$
" | ./preposition-extraction.bin 
^процес<n><m><sg><nom><def>$.. ^на<pr>$.. ^приватизација<n><f><sg><nom><ind><@P←>$

These patterns will later be translated using apertium and matched in the target-language corpus.

Preposition alignment[edit]

The patterns that were extracted in the previous process need to be aligned to their translations in the target language so the correct preposition can be extracted as a label. This way a training set can be created.

Usage: ./preposition-aligner.bin -s source-file -t target-file -tr translations-file -n number-of-features [-asrc allow-source] [-atrg allow-target] Options: -sl, --source a file with the sorce language sentences -tl, --target a file with the target language sentences -tr, --translations a file with the translations of the files -n number of features -atrg, --allow-only-target path to a file containing the allowed source-language prepositions -asrc, --allow-only-source path to a file containing the allowed target-language prepositions


preposition-aligner.bin -sl training-patterns-mk -tl training-patterns-en -tr extracted-patterns-nodef-train -n 2 | head -n 10

ефикасност--како$како--концепт$as a

The complete training phase[edit]

The training phase is done in two steps:

  • Extract patterns in the form of (n|vblex) (pr) (adj | det)* (n|vblex) from the source language corpus and translate the using apertium to the target language.
  • Go through the source language file again, matching those same patterns and trying to find their translations in the target language. If a translation is found, extract the features and correct preposition as a training-set example. You could theoretically choose any combination of features, however, the tools provided so far support only 3 different combinations:
    • 1-feature model -- extract an example in the following format: sl_nv1-sl_pr-sl_nv2<delimiter>tl_pr
    • 2-feature model -- extract an example in the following format: sl_nv1-sl_pr<delimiter>-sl_nv2<delimiter>tl_pr
    • 3-feature model -- extract an example in the following format: sl_nv1<delimiter>sl_pr<delimiter>sl_nv2<delimiter>tl_pr

sl_nv1, sl_nv1 and sl_pr stand for the first and second source language noun or verb, and for the source language preposition. tl_pr stands for the target language preposition, and that is the actual label used in classification


This is an example script that uses these two tools to create a training set:

cat | head -n 150000 | apertium -d ~/Apertium/apertium-mk-en mk-en-pretransfer > training-patterns-mk
cat training-patterns-mk | ~/Apertium/fpetkovski/morph-parser/preposition-extraction \
| lt-proc -g ~/Apertium/apertium-mk-en/en-mk.autogen.bin \
| apertium -d ~/Apertium/apertium-mk-en/ mk-en-postchunk > extracted-patterns-train

# In Macedonian, the definiteness of the noun is encoded in the noun itself, 
# while in English it is denoted by the article before the noun. 
# As a result, the extracted patterns after translation can have up to 5 tokens instead of the desired three. 
# That's why we want to remove the articles from the translated patterns.

# remove articles
cat extracted-patterns-train | sed 's/[ ]*\^[Tt]he<[^\$]*\$[ ]*//g' > extracted-patterns-nodef-train;

# tag the tl set
cat setimes.en | head -n 150000 | apertium -d ~/Apertium/apertium-en-es en-es-tagger > training-patterns-en

# alignment
preposition-aligner -sl training-patterns-mk -tl training-patterns-en -tr extracted-patterns-nodef-train -n 2 > training-set

And the output:

head -n 10 training-set


where the '$' character here serves as a delimiter.
Now you have a training set which you can use to train a classifier.

It should be noted that you can specify a list of both source-language and target-language prepositions that you want to allow in your training set. If such a list is specified for source-language prepositions, then patterns that do not contain those prepositions will not be extracted for the training set.

If a list is specified for target-language prepositions, then for those prepositions which are not in the list a new class will be created (class 'other'). This means that it will be left up to apertium to decide how to translate the source-language preposition if the classifier labels some example as a member of the class 'other'.

It is recommended that you use such a 'white-list' for target-language prepositions, and put the most common prepositions there, since for the less common ones there won't be enough coverage for those classes to be learned.

Applying the model[edit]

In order avoid depending on an external library, a naive bayes classifier was manually constructed, since that was the one used in the experiments. It can be found in the morph-parser directory and it can be used for training a model.

Once you have trained a model, you can insert it in the pipeline so it can be applied in the translation process. For the purpose of applying a naive bayes model, the preposition-selection tool was created which takes a biltrans output as an stream on standard input.

Usage: ./preposition-selection.bin [ -t | -l ] data_file -d delimiter Options: -t, --train use the data_file to train a model -l, --load load a trained model from the data_file -d, --delimiter sets the delimiter


cat ~/Desktop/setimes-en-mk-nikola/ | tail -n 50000 | apertium -d ~/Apertium/apertium-mk-en mk-en-biltrans |\
./preposition-selection --train "training-set" -d "$" | ./biltrans-to-end


cat ~/Desktop/setimes-en-mk-nikola/ | tail -n 50000 | apertium -d ~/Apertium/apertium-mk-en mk-en-biltrans |\
./preposition-selection --load "model" -d "$" | ./biltrans-to-end

The biltrans-to-end script should go through the rest of the pipeline, executing the transfer and generation processes.

For mk-en:

/usr/local/bin/apertium-transfer -b /home/philip/Apertium/apertium-mk-en/ /home/philip/Apertium/apertium-mk-en/mk-en.t1x.bin \
|/usr/local/bin/apertium-interchunk /home/philip/Apertium/apertium-mk-en/  /home/philip/Apertium/apertium-mk-en/mk-en.t2x.bin \
|/usr/local/bin/apertium-postchunk /home/philip/Apertium/apertium-mk-en/ /home/philip/Apertium/apertium-mk-en/mk-en.t3x.bin \
| sed 's/\[/\\[/g' | lt-proc -g ~/Apertium/apertium-mk-en/mk-en.autogen.bin \
| lt-proc -p ~/Apertium/apertium-mk-en/mk-en.autopgen.bin | apertium-retxt