Difference between revisions of "Final projects/Transducer"

From LING073
Jump to: navigation, search
(Created page with "* You can contribute straight to Apertium: ask for commit access. * To get random forms from your corpora for precision/recall measures: *# <pre>ca...")
 
Line 1: Line 1:
 
* You can contribute straight to Apertium: ask for [[:apertium:Commit_access|commit access]].
 
* You can contribute straight to Apertium: ask for [[:apertium:Commit_access|commit access]].
 
* To get random forms from your corpora for precision/recall measures:
 
* To get random forms from your corpora for precision/recall measures:
−
*# <pre>cat corpus1.txt corpus2.txt | apertium -d . abc-tagger | sed -r 's/\$\s*\^/\$\n\^/g' | cut -f1 -d'/' | sed 's/[\^\s\t]*//' | sort -Ru | head -n 1200 > words.txt</pre>
+
*# get 1200 random words: <pre>cat corpus1.txt corpus2.txt | apertium -d . abc-tagger | sed -r 's/\$\s*\^/\$\n\^/g' | cut -f1 -d'/' | sed 's/[\^\s\t]*//' | sort -Ru | head -n 1200 > words.txt</pre>
−
*# <pre>cat words.txt | apertium -d . abc-disam</pre>
+
*# get analyses from transducer: <pre>cat words.txt | apertium -d . abc-disam</pre>
 
*# Then do this again: [[Polished RBMT system#Hand-annotating corpora]]
 
*# Then do this again: [[Polished RBMT system#Hand-annotating corpora]]

Revision as of 20:43, 2 May 2017

  • You can contribute straight to Apertium: ask for commit access.
  • To get random forms from your corpora for precision/recall measures:
    1. get 1200 random words:
      cat corpus1.txt corpus2.txt | apertium -d . abc-tagger | sed -r 's/\$\s*\^/\$\n\^/g' | cut -f1 -d'/' | sed 's/[\^\s\t]*//' | sort -Ru | head -n 1200 > words.txt
    2. get analyses from transducer:
      cat words.txt | apertium -d . abc-disam
    3. Then do this again: Polished RBMT system#Hand-annotating corpora