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 07:06] mphi |
external:addicter [2011/05/16 07:47] 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 === | ||
- | || | + | | ^ Precision/ |
- | || | + | | ^ |
- | || meteor | + | ^ meteor |
- | || ter* | + | ^ ter* |0.106/ |
- | || hmm ||0.162/ | + | ^ hmm |
- | || lcs ||0.168/ | + | ^ lcs |
- | || 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** || | + | ^ gizainter |
- | || gizainter ||0.170/0.483/**0.252** ||0.049/0.137/**0.072** ||0.284/0.878/**0.429** ||0.029/0.409/**0.054** || | + | ^ gizadiag* |
- | || berkeley* | + | ^ berkeley* |0.200/ |
=== Explicit wrong lex choice detection === | === Explicit wrong lex choice detection === | ||
+ | * align input+czeng to reference+czeng and input+czeng to hypotheses+czeng | ||
+ | * extract hypothesis-to-reference alignments from there | ||
- | * align input+czeng to reference+czeng and input+czeng to hypotheses+czeng | + | | ^ Precision/ |
- | * extract hypothesis-to-reference alignments from there | + | | ^ |
+ | ^ czengdiag* |0.187/ | ||
+ | ^ czenginter |0.197/ | ||
- | || border=1 | + | === Alignment combinations === |
- | || || Precision/ | + | via weighed HMM |
- | || || Lex || Order || Punct || Miss || | + | |
- | || czengdiag* ||0.187/ | + | |
- | || czenginter ||0.197/ | + | |
- | === Alignment combinations via weighed HMM === | + | | ^ Precision/ |
- | + | | ^ Lex ^ Order ^ Punct ^ Miss ^ | |
- | || border=1 | + | ^ meteor+hmm |
- | || || Precision/ | + | ^ ter+hmm |
- | || | + | ^ gizadiag+hmm |
- | || meteor+hmm | + | ^ gizainter+hmm |
- | || ter+hmm | + | ^ berkeley+hmm |
- | || gizadiag+hmm | + | ^ czengdiag+hmm |
- | || gizainter+hmm | + | ^ czenginter+hmm |
- | || berkeley+hmm | + | | ||||| |
- | || czengdiag+hmm | + | ^ berkeley+czenginter+hmm |0.219/ |
- | || czenginter+hmm | + | ^ berkeley+czenginter+gizainter+hmm |0.220/ |
- | || |||||||||| | + | ^ berkeley+czenginter+meteor+hmm |0.220/ |
- | || berkeley+czenginter+hmm | + | ^ berkeley+czenginter+meteor+gizainter+hmm |0.221/ |
- | || berkeley+czenginter+gizainter+hmm | + | |
- | || berkeley+czenginter+meteor+hmm | + | |
==== TODOs ==== | ==== TODOs ==== | ||
- | | + | * test alignment with synonym detection (cz_wn required) = separating |
- | | + | |
* order evaluation | * order evaluation | ||
* a lot of background research | * a lot of background research | ||
Line 55: | Line 55: | ||
* 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: " | ||