The introductory page on the Addicter project is here.

This page lies in the external name space and is intended for collaboration with people outside of ÚFAL.

• test alignment with synonym detection (cz_wn required) = separating lex:: and disam::
• try misplaced phrase detection
  • parse the reference, extrapolate unto the hypothesis via word alignment, get phrases from there
  • group adjacent words aligned to the same word? (imitation)
• order evaluation
  • currently finds misplaced items, but their shift distances are off
  • not important for ows vs owl, but
    • to fix – for every misplaced token
      • if it (and only it) were to be moved in the original permutation, what would be the best place?
      • evaluate with nr. of intersections
• try domain adaptation for word alignment with the “via source” alignment (EMNLP 2011 paper)
• technical
  • comb and comment the code
  • add help files
  • integrate with the rest of Addicter
• approach applicable to learner's corpora
  • see Anne Lüdelig, TLT9
• try Blast (Sara's program for translation error markup)
• alternative to reference-based evaluation: “Inconsistencies in Penn parsing”, M. Dickinson

txt

hmm = lightweight direct alignment method (in our ACL/TSD article)
gizainter = GIZA++, intersection – applied to hypotheses+references directly
gizadiag = GIZA++, grow-diag – applied to hypotheses+references directly
czenginter = align source+CzEng to reference+CzEng, and source+CzEng to hypotheses+CzEng with GIZA++, intersection, extract hypothesis-reference alignments from there (“Dan's method”)
czengdiag = same, but with GIZA++ grow-diag

* non-1-to-1 alignments, converted to 1-to-1 via “align-hmm.pl -x -a …”

via weighed HMM