Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
|
external:addicter [2011/05/16 07:15] mphi |
external:addicter [2011/05/16 08:10] mphi |
||
|---|---|---|---|
| Line 6: | Line 6: | ||
| ==== Word Alignment -- Progress and Results ==== | ==== Word Alignment -- Progress and Results ==== | ||
| + | |||
| + | === Latest best results === | ||
| + | [[http:// | ||
| === Alternative model comparison === | === Alternative model comparison === | ||
| + | |||
| + | 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, | ||
| + | czengdiag = same, but with GIZA++ grow-diag | ||
| + | |||
| | | | | ||
| | | | | ||
| - | ^ meteor | ||
| ^ ter* |0.106/ | ^ ter* |0.106/ | ||
| + | ^ meteor | ||
| ^ hmm | ^ hmm | ||
| ^ lcs | ^ lcs | ||
| - | ^ gizadiag* |0.183/ | ||
| ^ gizainter |0.170/ | ^ gizainter |0.170/ | ||
| - | ^ berkeley* |0.200/0.540/**0.291** |0.050/0.330/**0.087** |0.292/0.844/**0.434** |0.039/0.267/**0.068** | | + | ^ gizadiag* |0.183/0.512/**0.270** |0.044/0.250/**0.075** |0.285/0.784/**0.417** |0.038/0.224/**0.065** | |
| - | + | ||
| - | === Explicit wrong lex choice detection === | + | |
| - | * align input+czeng to reference+czeng and input+czeng to hypotheses+czeng | + | |
| - | * extract hypothesis-to-reference alignments from there | + | |
| - | + | ||
| - | | ^ Precision/ | + | |
| - | | ^ | + | |
| ^ czengdiag* |0.187/ | ^ czengdiag* |0.187/ | ||
| + | ^ berkeley* |0.200/ | ||
| ^ czenginter |0.197/ | ^ czenginter |0.197/ | ||
| + | |||
| + | * non-1-to-1 alignments, converted to 1-to-1 via " | ||
| === Alignment combinations === | === Alignment combinations === | ||
| Line 32: | Line 37: | ||
| | | | | ||
| | | | | ||
| - | ^ meteor+hmm | ||
| ^ ter+hmm | ^ ter+hmm | ||
| + | ^ meteor+hmm | ||
| ^ gizadiag+hmm | ^ gizadiag+hmm | ||
| ^ gizainter+hmm | ^ gizainter+hmm | ||
| Line 40: | Line 45: | ||
| ^ czenginter+hmm | ^ czenginter+hmm | ||
| | ||||| | | ||||| | ||
| - | ^ berkeley+czenginter+hmm |0.219/ | + | ^ berk+czengint+hmm |0.219/ |
| - | ^ berkeley+czenginter+gizainter+hmm |0.220/ | + | ^ berk+czengint+gizaint+hmm |0.220/ |
| - | ^ berkeley+czenginter+meteor+hmm |0.220/ | + | ^ berk+czengint+meteor+hmm |0.220/ |
| + | ^ berk+czengint+meteor+gizaint+hmm |0.221/ | ||
| ==== TODOs ==== | ==== TODOs ==== | ||
| - | * try domain adaptation for word alignment, EMNLP 2011 paper | ||
| * test alignment with synonym detection (cz_wn required) = separating '' | * test alignment with synonym detection (cz_wn required) = separating '' | ||
| * order evaluation | * order evaluation | ||
| Line 53: | Line 58: | ||
| * if it (and only it) were to be moved in the original permutation, | * if it (and only it) were to be moved in the original permutation, | ||
| * evaluate with nr. of intersections | * evaluate with nr. of intersections | ||
| + | * try domain adaptation for word alignment, EMNLP 2011 paper | ||
| * comb and comment the code | * comb and comment the code | ||
| * add help files | * add help files | ||
| * integrate with the rest of Addicter | * integrate with the rest of Addicter | ||
| - | * learner' | + | * approach applicable to learner' |
| * see Anne Lüdelig, TLT9 | * see Anne Lüdelig, TLT9 | ||
| - | * adapt to Sara's program | + | * adapt Addicter |
| * alternative to reference-based evaluation: " | * alternative to reference-based evaluation: " | ||