Difference between revisions of "RTE5 - Ablation Tests"

From ACL Wiki
Jump to navigation Jump to search
Line 1: Line 1:
 +
{|class="wikitable sortable" cellpadding="3" cellspacing="0" border="1"
  
 +
|- bgcolor="#CDCDCD"
 +
! Ablated Resource
 +
! Team Run
 +
! Relative accuracy - 2way
 +
! Relative accuracy - 3way
 +
! Resource Usage Description
 +
 +
|- bgcolor="#ECECEC" "align="left"
 +
| Acronym guide
 +
| Siel_093.3way
 +
| style="text-align: right;"|0
 +
| style="text-align: right;"|0
 +
| Acronym Resolution
 +
 +
|- bgcolor="#ECECEC" "align="left"
 +
| Acronym guide + <br>Acronym_rules by UAIC
 +
| UAIC20091.3way
 +
| style="text-align: right;"| +0.0017
 +
| style="text-align: right;"| +0.0016
 +
| We start from acronym-guide, but additional we use a rule that consider for expressions like Xaaaa Ybbbb Zcccc the acronym XYZ, regardless of length of text with this form.
 +
 +
|- bgcolor="#ECECEC" "align="left"
 +
| DIRT
 +
| BIU1.2way
 +
| style="text-align: right;"| +0.0133
 +
| style="text-align: right;"|
 +
| Inference rules
 +
 +
|- bgcolor="#ECECEC" "align="left"
 +
| DIRT
 +
| Boeing3.3way
 +
| style="text-align: right;"| -0.0117
 +
| style="text-align: right;"| 0
 +
|
 +
 +
|- bgcolor="#ECECEC" "align="left"
 +
| DIRT
 +
| UAIC20091.3way
 +
| style="text-align: right;"| +0,0017
 +
| style="text-align: right;"| +0,0033
 +
| We transform text and hypothesis with MINIPAR into dependency trees: use of DIRT relations to map verbs in T with verbs in H
 +
 +
|- bgcolor="#ECECEC" "align="left"
 +
| Framenet
 +
| DLSIUAES1.2way
 +
| style="text-align: right;"| +0,0116
 +
| style="text-align: right;"|
 +
| frame-to-frame similarity metric
 +
 +
|- bgcolor="#ECECEC" "align="left"
 +
| Framenet
 +
| DLSIUAES1.3way
 +
| style="text-align: right;"| -0,0017
 +
| style="text-align: right;"| -0,0017
 +
| frame-to-frame similarity metric
 +
 +
|- bgcolor="#ECECEC" "align="left"
 +
| Framenet
 +
| UB.dmirg3.2way
 +
| style="text-align: right;"| 0
 +
| style="text-align: right;"|
 +
|
 +
 +
|- bgcolor="#ECECEC" "align="left"
 +
| Grady Ward’s MOBY Thesaurus + <br>Roget's Thesaurus
 +
| VensesTeam2.2way
 +
| style="text-align: right;"| +0.0283
 +
| style="text-align: right;"|
 +
| Semantic fields are used as semantic similarity matching, in all cases of non identical lemmas
 +
 +
 +
|}

Revision as of 08:08, 24 November 2009

Ablated Resource Team Run Relative accuracy - 2way Relative accuracy - 3way Resource Usage Description
Acronym guide Siel_093.3way 0 0 Acronym Resolution
Acronym guide +
Acronym_rules by UAIC
UAIC20091.3way +0.0017 +0.0016 We start from acronym-guide, but additional we use a rule that consider for expressions like Xaaaa Ybbbb Zcccc the acronym XYZ, regardless of length of text with this form.
DIRT BIU1.2way +0.0133 Inference rules
DIRT Boeing3.3way -0.0117 0
DIRT UAIC20091.3way +0,0017 +0,0033 We transform text and hypothesis with MINIPAR into dependency trees: use of DIRT relations to map verbs in T with verbs in H
Framenet DLSIUAES1.2way +0,0116 frame-to-frame similarity metric
Framenet DLSIUAES1.3way -0,0017 -0,0017 frame-to-frame similarity metric
Framenet UB.dmirg3.2way 0
Grady Ward’s MOBY Thesaurus +
Roget's Thesaurus
VensesTeam2.2way +0.0283 Semantic fields are used as semantic similarity matching, in all cases of non identical lemmas