Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Last revision Both sides next revision | ||
external:addicter [2011/05/16 07:59] mphi |
external:addicter [2011/05/22 09:27] mphi |
||
---|---|---|---|
Line 4: | Line 4: | ||
This page lies in the external name space and is intended for collaboration with people outside of ÚFAL. | This page lies in the external name space and is intended for collaboration with people outside of ÚFAL. | ||
+ | |||
+ | ==== TODOs ==== | ||
+ | * test alignment with synonym detection (cz_wn required) = separating '' | ||
+ | * order evaluation | ||
+ | * a lot of background research | ||
+ | * currently finds misplaced items, but their shift distances are off | ||
+ | * to fix -- for every misplaced token | ||
+ | * if it (and only it) were to be moved in the original permutation, | ||
+ | * evaluate with nr. of intersections | ||
+ | * try domain adaptation for word alignment, EMNLP 2011 paper | ||
+ | * comb and comment the code | ||
+ | * add help files | ||
+ | * integrate with the rest of Addicter | ||
+ | * approach applicable to learner' | ||
+ | * see Anne Lüdelig, TLT9 | ||
+ | * adapt Addicter to Sara's program | ||
+ | * alternative to reference-based evaluation: " | ||
==== Word Alignment -- Progress and Results ==== | ==== Word Alignment -- Progress and Results ==== | ||
Line 11: | Line 28: | ||
=== 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 | ||
+ | |||
| | | | ||
| | | | ||
Line 19: | Line 43: | ||
^ gizainter |0.170/ | ^ gizainter |0.170/ | ||
^ gizadiag* |0.183/ | ^ gizadiag* |0.183/ | ||
+ | ^ czengdiag* |0.187/ | ||
^ berkeley* |0.200/ | ^ berkeley* |0.200/ | ||
+ | ^ czenginter |0.197/ | ||
- | === Explicit wrong lex choice detection === | + | * non-1-to-1 alignments, converted |
- | | + | |
- | * align input+czeng | + | |
- | * extract hypothesis-to-reference alignments from there | + | |
- | + | ||
- | | ^ Precision/ | + | |
- | | ^ | + | |
- | ^ czengdiag* |0.187/0.514/**0.275** |0.069/ | + | |
- | ^ czenginter |0.197/ | + | |
=== Alignment combinations === | === Alignment combinations === | ||
Line 49: | Line 67: | ||
^ berk+czengint+meteor+gizaint+hmm |0.221/ | ^ berk+czengint+meteor+gizaint+hmm |0.221/ | ||
- | ==== TODOs ==== | ||
- | * test alignment with synonym detection (cz_wn required) = separating '' | ||
- | * order evaluation | ||
- | * a lot of background research | ||
- | * currently finds misplaced items, but their shift distances are off | ||
- | * to fix -- for every misplaced token | ||
- | * if it (and only it) were to be moved in the original permutation, | ||
- | * evaluate with nr. of intersections | ||
- | * try domain adaptation for word alignment, EMNLP 2011 paper | ||
- | * comb and comment the code | ||
- | * add help files | ||
- | * integrate with the rest of Addicter | ||
- | * approach applicable to learner' | ||
- | * see Anne Lüdelig, TLT9 | ||
- | * adapt Addicter to Sara's program | ||
- | * alternative to reference-based evaluation: " | ||