ReTraTos

ReTraTos is a toolbox to build linguistic resources useful for machine translation (MT): bilingual dictionaries and transfer rules. The induction systems and open linguistic data can be used with the Apertium toolbox to build open-source MT systems.

Input format

The input sentences need to be given in two separate files, for example en.txt for English and pt.txt for Portuguese.

pt.txt

  <s snum=1>Os/O<det><def><m><pl>:1 alunos/aluno<n><m><pl>:2 do/de<pr>+o<det><def><m><sg>:3_4 colégio/colégio<n><m><sg>:5
 
  ...

en.txt

  <s snum=1>The/The<det><def><sp>:1 students/student<n><pl>:2 of/of<pr>:3 the/the<det><def><sp>:3 school/school<n><pl>:5

  ...

Usage

ReTraTos_lex

You will need the header and footer of a bilingual dictionary in two separate files, for example, dic_header.txt and dic_footer.txt (see the examples in the package). Example sentences, in the format described above will be in the files en.txt and pl.txt.

$ ReTraTos_lex -s pt.txt -t en.txt -b dic_header.txt -e dic_footer.txt 

PRE-PROCESSAMENTO

        Reading the examples ...  100 examples read
        Reading the examples ...  100 examples read

GERANDO LEXICO

        Generating source-target dictionary ... OK
        Generating target-source dictionary ... OK
        Processing bilingual dictionary ... OK
        Generalizing bilingual dictionary ... OK
        Cleaning equal attributes ... OK

IMPRIMINDO LEXICO

        Printing bilingual dictionary ... OK

The output file will be ReTraTos_lex_ptXen_1.dix.

See also

• Using GIZA++

External links

• ReTraTos: Homepage
• ReTraTos: SVN

Further reading

• Helena M. Caseli, Maria das Graças V. Nunes, Mikel L. Forcada, "From free shallow monolingual resources to machine translation systems: easing the task", in Mixing Approaches To Machine Translation, MATMT2008, proceedings (Donostia, Spain, Feb. 14, 2008), pp. 41--48