Difference between revisions of "RTE5 - Ablation Tests"

From ACL Wiki
Jump to navigation Jump to search
Line 11: Line 11:
 
| Acronym guide
 
| Acronym guide
 
| Siel_093.3way
 
| Siel_093.3way
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
 
| Acronym Resolution
 
| Acronym Resolution
  
Line 18: Line 18:
 
| Acronym guide + <br>UAIC_Acronym_rules  
 
| Acronym guide + <br>UAIC_Acronym_rules  
 
| UAIC20091.3way
 
| UAIC20091.3way
| style="text-align: right;"| 0.0017
+
| style="text-align: center;"| 0.0017
| style="text-align: right;"| 0.0016
+
| style="text-align: center;"| 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.
 
| 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.
  
Line 25: Line 25:
 
| DIRT
 
| DIRT
 
| BIU1.2way
 
| BIU1.2way
| style="text-align: right;"| 0.0133
+
| style="text-align: center;"| 0.0133
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| Inference rules
 
| Inference rules
  
Line 32: Line 32:
 
| DIRT
 
| DIRT
 
| Boeing3.3way
 
| Boeing3.3way
| style="text-align: right;"| -0.0117
+
| style="text-align: center;"| -0.0117
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
 
|  
 
|  
  
Line 39: Line 39:
 
| DIRT
 
| DIRT
 
| UAIC20091.3way
 
| UAIC20091.3way
| style="text-align: right;"| 0.0017
+
| style="text-align: center;"| 0.0017
| style="text-align: right;"| 0.0033
+
| style="text-align: center;"| 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
 
| We transform text and hypothesis with MINIPAR into dependency trees: use of DIRT relations to map verbs in T with verbs in H
  
Line 46: Line 46:
 
| Framenet
 
| Framenet
 
| DLSIUAES1.2way
 
| DLSIUAES1.2way
| style="text-align: right;"| 0.0116
+
| style="text-align: center;"| 0.0116
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| frame-to-frame similarity metric
 
| frame-to-frame similarity metric
  
Line 53: Line 53:
 
| Framenet
 
| Framenet
 
| DLSIUAES1.3way
 
| DLSIUAES1.3way
| style="text-align: right;"| -0.0017
+
| style="text-align: center;"| -0.0017
| style="text-align: right;"| -0.0017
+
| style="text-align: center;"| -0.0017
 
| frame-to-frame similarity metric
 
| frame-to-frame similarity metric
  
Line 60: Line 60:
 
| Framenet
 
| Framenet
 
| UB.dmirg3.2way
 
| UB.dmirg3.2way
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
|  
 
|  
  
Line 67: Line 67:
 
| Grady Ward’s MOBY Thesaurus + <br>Roget's Thesaurus
 
| Grady Ward’s MOBY Thesaurus + <br>Roget's Thesaurus
 
| VensesTeam2.2way
 
| VensesTeam2.2way
| style="text-align: right;"| 0.0283
+
| style="text-align: center;"| 0.0283
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| Semantic fields are used as semantic similarity matching, in all cases of non identical lemmas
 
| Semantic fields are used as semantic similarity matching, in all cases of non identical lemmas
  
Line 74: Line 74:
 
| MontyLingua Tool
 
| MontyLingua Tool
 
| Siel_093.3way
 
| Siel_093.3way
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
 
| For the VerbOcean, the verbs have to be in the base form. We used the "MontyLingua" tool to convert the verbs into their base form  
 
| For the VerbOcean, the verbs have to be in the base form. We used the "MontyLingua" tool to convert the verbs into their base form  
  
Line 81: Line 81:
 
| NEGATION_rules by UAIC
 
| NEGATION_rules by UAIC
 
| UAIC20091.3way
 
| UAIC20091.3way
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
| style="text-align: right;"| -0.0134
+
| style="text-align: center;"| -0.0134
 
| Negation rules check in the dependency trees on verbs descending branches to see if some categories of words that change the meaning are found.
 
| Negation rules check in the dependency trees on verbs descending branches to see if some categories of words that change the meaning are found.
  
Line 88: Line 88:
 
| NER
 
| NER
 
| UI_ccg1.2way
 
| UI_ccg1.2way
| style="text-align: right;"| 0.0483
+
| style="text-align: center;"| 0.0483
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| Named Entity recognition/comparison
 
| Named Entity recognition/comparison
  
Line 95: Line 95:
 
| PropBank
 
| PropBank
 
| cswhu1.3way
 
| cswhu1.3way
| style="text-align: right;"| 0.0200
+
| style="text-align: center;"| 0.0200
| style="text-align: right;"| 0.0317
+
| style="text-align: center;"| 0.0317
 
| syntactic and semantic parsing
 
| syntactic and semantic parsing
  
Line 102: Line 102:
 
| Stanford NER
 
| Stanford NER
 
| QUANTA1.2way
 
| QUANTA1.2way
| style="text-align: right;"| 0.0067
+
| style="text-align: center;"| 0.0067
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| We use Named Entity similarity as a feature
 
| We use Named Entity similarity as a feature
  
Line 109: Line 109:
 
| Stopword list
 
| Stopword list
 
| FBKirst1.2way
 
| FBKirst1.2way
| style="text-align: right;"| 0.0150
+
| style="text-align: center;"| 0.0150
| style="text-align: right;"| -0.1028
+
| style="text-align: center;"| -0.1028
 
|  
 
|  
  
Line 116: Line 116:
 
| Training data from RTE1, 2, 3
 
| Training data from RTE1, 2, 3
 
| PeMoZa3.2way
 
| PeMoZa3.2way
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
|  
 
|  
  
Line 123: Line 123:
 
| Training data from RTE1, 2, 3
 
| Training data from RTE1, 2, 3
 
| PeMoZa3.2way
 
| PeMoZa3.2way
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
|  
 
|  
  
Line 130: Line 130:
 
| Training data from RTE2
 
| Training data from RTE2
 
| PeMoZa3.2way
 
| PeMoZa3.2way
| style="text-align: right;"| 0.0066
+
| style="text-align: center;"| 0.0066
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
|  
 
|  
  
Line 137: Line 137:
 
| Training data from RTE2, 3
 
| Training data from RTE2, 3
 
| PeMoZa3.2way
 
| PeMoZa3.2way
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
|  
 
|  
  
Line 144: Line 144:
 
| VerbOcean
 
| VerbOcean
 
| DFKI1.3way
 
| DFKI1.3way
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
| style="text-align: right;"| 0.0017
+
| style="text-align: center;"| 0.0017
 
|  
 
|  
  
Line 151: Line 151:
 
| VerbOcean
 
| VerbOcean
 
| DFKI2.3way
 
| DFKI2.3way
| style="text-align: right;"| 0.0033
+
| style="text-align: center;"| 0.0033
| style="text-align: right;"| 0.0050
+
| style="text-align: center;"| 0.0050
 
|  
 
|  
  
Line 158: Line 158:
 
| VerbOcean
 
| VerbOcean
 
| DFKI3.3way
 
| DFKI3.3way
| style="text-align: right;"| 0.0017
+
| style="text-align: center;"| 0.0017
| style="text-align: right;"| 0.0017
+
| style="text-align: center;"| 0.0017
 
|  
 
|  
  
Line 165: Line 165:
 
| VerbOcean
 
| VerbOcean
 
| FBKirst1.2way
 
| FBKirst1.2way
| style="text-align: right;"| -0.0016
+
| style="text-align: center;"| -0.0016
| style="text-align: right;"| -0.1028
+
| style="text-align: center;"| -0.1028
 
| Rules extracted from VerbOcean
 
| Rules extracted from VerbOcean
  
Line 172: Line 172:
 
| VerbOcean
 
| VerbOcean
 
| QUANTA1.2way
 
| QUANTA1.2way
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| We use "opposite-of" relation in VerbOcean as a feature
 
| We use "opposite-of" relation in VerbOcean as a feature
  
Line 179: Line 179:
 
| VerbOcean
 
| VerbOcean
 
| Siel_093.3way
 
| Siel_093.3way
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
 
| Similarity/anthonymy/unrelatedness between verbs
 
| Similarity/anthonymy/unrelatedness between verbs
  
Line 186: Line 186:
 
| WikiPedia
 
| WikiPedia
 
| BIU1.2way
 
| BIU1.2way
| style="text-align: right;"| -0.0100
+
| style="text-align: center;"| -0.0100
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| Lexical rules extracted from Wikipedia definition sentences, title parenthesis, redirect and hyperlink relations
 
| Lexical rules extracted from Wikipedia definition sentences, title parenthesis, redirect and hyperlink relations
  
Line 193: Line 193:
 
| WikiPedia
 
| WikiPedia
 
| cswhu1.3way
 
| cswhu1.3way
| style="text-align: right;"| 0.0133
+
| style="text-align: center;"| 0.0133
| style="text-align: right;"| 0.0334
+
| style="text-align: center;"| 0.0334
 
| Lexical semantic rules
 
| Lexical semantic rules
  
Line 200: Line 200:
 
| WikiPedia
 
| WikiPedia
 
| FBKirst1.2way
 
| FBKirst1.2way
| style="text-align: right;"| 0.0100
+
| style="text-align: center;"| 0.0100
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| Rules extracted from WP using Latent Semantic Analysis (LSA)
 
| Rules extracted from WP using Latent Semantic Analysis (LSA)
  
Line 207: Line 207:
 
| WikiPedia
 
| WikiPedia
 
| UAIC20091.3way
 
| UAIC20091.3way
| style="text-align: right;"| 0.0117
+
| style="text-align: center;"| 0.0117
| style="text-align: right;"| 0.0150
+
| style="text-align: center;"| 0.0150
 
| Relations between named entities
 
| Relations between named entities
  
Line 214: Line 214:
 
| Wikipedia + <br>NER's (LingPipe, GATE) + <br>Perl patterns
 
| Wikipedia + <br>NER's (LingPipe, GATE) + <br>Perl patterns
 
| UAIC20091.3way
 
| UAIC20091.3way
| style="text-align: right;"| 0.0617
+
| style="text-align: center;"| 0.0617
| style="text-align: right;"| 0.0500
+
| style="text-align: center;"| 0.0500
 
| NE module: NERs, in order to identify Persons, Locations, Jobs, Languages, etc; Perl patterns built by us for RTE4 in order to identify numbers and dates; our own resources extracted from Wikipedia in order to identify a "distance" between one name entity from hypothesis and name entities from text
 
| NE module: NERs, in order to identify Persons, Locations, Jobs, Languages, etc; Perl patterns built by us for RTE4 in order to identify numbers and dates; our own resources extracted from Wikipedia in order to identify a "distance" between one name entity from hypothesis and name entities from text
  
Line 221: Line 221:
 
| WordNet
 
| WordNet
 
| AUEBNLP1.3way
 
| AUEBNLP1.3way
| style="text-align: right;"| -0.0200
+
| style="text-align: center;"| -0.0200
| style="text-align: right;"| -0.0267
+
| style="text-align: center;"| -0.0267
 
| Synonyms
 
| Synonyms
  
Line 228: Line 228:
 
| WordNet
 
| WordNet
 
| BIU1.2way
 
| BIU1.2way
| style="text-align: right;"| 0.0250
+
| style="text-align: center;"| 0.0250
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| Synonyms, hyponyms (2 levels away from the original term), hyponym_instance and derivations
 
| Synonyms, hyponyms (2 levels away from the original term), hyponym_instance and derivations
  
Line 235: Line 235:
 
| WordNet
 
| WordNet
 
| Boeing3.3way
 
| Boeing3.3way
| style="text-align: right;"| 0.0400  
+
| style="text-align: center;"| 0.0400  
| style="text-align: right;"| 0.0567
+
| style="text-align: center;"| 0.0567
 
|  
 
|  
  
Line 242: Line 242:
 
| WordNet
 
| WordNet
 
| DFKI1.3way
 
| DFKI1.3way
| style="text-align: right;"| -0.0017  
+
| style="text-align: center;"| -0.0017  
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
 
|  
 
|  
  
Line 249: Line 249:
 
| WordNet
 
| WordNet
 
| DFKI2.3way
 
| DFKI2.3way
| style="text-align: right;"| 0.0016
+
| style="text-align: center;"| 0.0016
| style="text-align: right;"| 0.0034
+
| style="text-align: center;"| 0.0034
 
|  
 
|  
  
Line 256: Line 256:
 
| WordNet
 
| WordNet
 
| DFKI3.3way
 
| DFKI3.3way
| style="text-align: right;"| 0.0017
+
| style="text-align: center;"| 0.0017
| style="text-align: right;"| 0.0017
+
| style="text-align: center;"| 0.0017
 
|  
 
|  
  
Line 263: Line 263:
 
| WordNet
 
| WordNet
 
| DLSIUAES1.2way
 
| DLSIUAES1.2way
| style="text-align: right;"| 0.0083
+
| style="text-align: center;"| 0.0083
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| Similarity between lemmata, computed by WordNet-based metrics
 
| Similarity between lemmata, computed by WordNet-based metrics
  
Line 270: Line 270:
 
| WordNet
 
| WordNet
 
| DLSIUAES1.3way
 
| DLSIUAES1.3way
| style="text-align: right;"| -0.0050
+
| style="text-align: center;"| -0.0050
| style="text-align: right;"| -0.0033
+
| style="text-align: center;"| -0.0033
 
| Similarity between lemmata, computed by WordNet-based metrics
 
| Similarity between lemmata, computed by WordNet-based metrics
  
Line 277: Line 277:
 
| WordNet
 
| WordNet
 
| JU_CSE_TAC1.2way
 
| JU_CSE_TAC1.2way
| style="text-align: right;"| 0.0034
+
| style="text-align: center;"| 0.0034
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| WordNet based Unigram match
 
| WordNet based Unigram match
  
Line 284: Line 284:
 
| WordNet
 
| WordNet
 
| PeMoZa1.2way
 
| PeMoZa1.2way
| style="text-align: right;"| -0.0050
+
| style="text-align: center;"| -0.0050
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| Derivational Morphology from WordNet
 
| Derivational Morphology from WordNet
  
Line 291: Line 291:
 
| WordNet
 
| WordNet
 
| PeMoZa1.2way
 
| PeMoZa1.2way
| style="text-align: right;"| 0.0133
+
| style="text-align: center;"| 0.0133
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| Verb Entailment from Wordnet
 
| Verb Entailment from Wordnet
  
Line 298: Line 298:
 
| WordNet
 
| WordNet
 
| PeMoZa2.2way
 
| PeMoZa2.2way
| style="text-align: right;"| 0.0100
+
| style="text-align: center;"| 0.0100
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| Derivational Morphology from WordNet
 
| Derivational Morphology from WordNet
  
Line 305: Line 305:
 
| WordNet
 
| WordNet
 
| PeMoZa2.2way
 
| PeMoZa2.2way
| style="text-align: right;"| -0.0033
+
| style="text-align: center;"| -0.0033
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| Verb Entailment from Wordnet
 
| Verb Entailment from Wordnet
  
Line 312: Line 312:
 
| WordNet
 
| WordNet
 
| QUANTA1.2way
 
| QUANTA1.2way
| style="text-align: right;"| -0.0017
+
| style="text-align: center;"| -0.0017
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
| We use several relations from wordnet, such as synonyms, hyponym, hypernym et al.
 
| We use several relations from wordnet, such as synonyms, hyponym, hypernym et al.
  
Line 319: Line 319:
 
| WordNet
 
| WordNet
 
| Sagan1.3way
 
| Sagan1.3way
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
| style="text-align: right;"| -0.0083
+
| style="text-align: center;"| -0.0083
 
| The system is based on machine learning approach. The ablation test was obtained with 2 less features using WordNet in the training and testing steps.
 
| The system is based on machine learning approach. The ablation test was obtained with 2 less features using WordNet in the training and testing steps.
  
Line 327: Line 327:
 
| WordNet
 
| WordNet
 
| Siel_093.3way
 
| Siel_093.3way
| style="text-align: right;"| 0.0034
+
| style="text-align: center;"| 0.0034
| style="text-align: right;"| -0.0017
+
| style="text-align: center;"| -0.0017
 
| Similarity between nouns using WN tool
 
| Similarity between nouns using WN tool
  
Line 334: Line 334:
 
| WordNet
 
| WordNet
 
| ssl1.3way
 
| ssl1.3way
| style="text-align: right;"| 0
+
| style="text-align: center;"| 0
| style="text-align: right;"| 0.0067
+
| style="text-align: center;"| 0.0067
 
| WordNet Analysis
 
| WordNet Analysis
  
 
|- bgcolor="#ECECEC" "align="left"
 
|- bgcolor="#ECECEC" "align="left"
 
| WordNet
 
| WordNet
|  
+
| UB.dmirg3.2way
| style="text-align: right;"|  
+
| style="text-align: center;"| 0
| style="text-align: right;"|  
+
| style="text-align: center;"|  
 
|  
 
|  
  
 
|- bgcolor="#ECECEC" "align="left"
 
|- bgcolor="#ECECEC" "align="left"
 
| WordNet
 
| WordNet
 +
| UI_ccg1.2way
 +
| style="text-align: center;"| 0.0400
 +
| style="text-align: center;"|
 +
| word similarity == identity
 +
 +
|- bgcolor="#ECECEC" "align="left"
 +
| WordNet +<br>FrameNet
 +
| UB.dmirg3.2way
 +
| style="text-align: center;"| 0
 +
| style="text-align: center;"|
 
|  
 
|  
| style="text-align: right;"|  
+
 
| style="text-align: right;"|  
+
|- bgcolor="#ECECEC" "align="left"
 +
| WordNet +<br>VerbOcean
 +
| DFKI1.3way
 +
| style="text-align: center;"| 0
 +
| style="text-align: center;"| 0.0017
 
|  
 
|  
  
 
|- bgcolor="#ECECEC" "align="left"
 
|- bgcolor="#ECECEC" "align="left"
| WordNet
+
| WordNet +<br>VerbOcean
 +
| DFKI2.3way
 +
| style="text-align: center;"| 0.0050
 +
| style="text-align: center;"| 0.0067
 
|  
 
|  
| style="text-align: right;"|  
+
 
| style="text-align: right;"|  
+
|- bgcolor="#ECECEC" "align="left"
 +
| WordNet +<br>VerbOcean
 +
| DFKI3.3way
 +
| style="text-align: center;"| 0.0017
 +
| style="text-align: center;"| 0.0017
 
|  
 
|  
  
 
|- bgcolor="#ECECEC" "align="left"
 
|- bgcolor="#ECECEC" "align="left"
| WordNet
+
| WordNet +<br>VerbOcean
|  
+
| UAIC20091.3way
| style="text-align: right;"|  
+
| style="text-align: center;"| 0.0200
| style="text-align: right;"|  
+
| style="text-align: center;"| 0.0150
|  
+
| Contradiction identification
 +
 
 +
|- bgcolor="#ECECEC" "align="left"
 +
| WordNet +<br>VerbOcean + <br>DLSIUAES_negation_list
 +
| DLSIUAES1.2way
 +
| style="text-align: center;"| 0.0066
 +
| style="text-align: center;"|
 +
| Antonym relations between verbs (VO+WN); polarity based on negation terms (short list constructed by ourselves)
 +
 
 +
|- bgcolor="#ECECEC" "align="left"
 +
| WordNet +<br>VerbOcean + <br>DLSIUAES_negation_list
 +
| DLSIUAES1.3way
 +
| style="text-align: center;"| -0.0100
 +
| style="text-align: center;"| -0.0050
 +
| Antonym relations between verbs (VO+WN); polarity based on negation terms (short list constructed by ourselves)
  
 
|- bgcolor="#ECECEC" "align="left"
 
|- bgcolor="#ECECEC" "align="left"
| WordNet
+
| WordNet +<br>XWordNet
|  
+
| UAIC20091.3way
| style="text-align: right;"|  
+
| style="text-align: center;"| 0.0100
| style="text-align: right;"|  
+
| style="text-align: center;"| 0.0133
|  
+
| Synonymy, hyponymy and hypernymy and eXtended WordNet relation
  
 
|}
 
|}

Revision as of 12:30, 25 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 +
UAIC_Acronym_rules
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
MontyLingua Tool Siel_093.3way 0 0 For the VerbOcean, the verbs have to be in the base form. We used the "MontyLingua" tool to convert the verbs into their base form
NEGATION_rules by UAIC UAIC20091.3way 0 -0.0134 Negation rules check in the dependency trees on verbs descending branches to see if some categories of words that change the meaning are found.
NER UI_ccg1.2way 0.0483 Named Entity recognition/comparison
PropBank cswhu1.3way 0.0200 0.0317 syntactic and semantic parsing
Stanford NER QUANTA1.2way 0.0067 We use Named Entity similarity as a feature
Stopword list FBKirst1.2way 0.0150 -0.1028
Training data from RTE1, 2, 3 PeMoZa3.2way 0
Training data from RTE1, 2, 3 PeMoZa3.2way 0
Training data from RTE2 PeMoZa3.2way 0.0066
Training data from RTE2, 3 PeMoZa3.2way 0
VerbOcean DFKI1.3way 0 0.0017
VerbOcean DFKI2.3way 0.0033 0.0050
VerbOcean DFKI3.3way 0.0017 0.0017
VerbOcean FBKirst1.2way -0.0016 -0.1028 Rules extracted from VerbOcean
VerbOcean QUANTA1.2way 0 We use "opposite-of" relation in VerbOcean as a feature
VerbOcean Siel_093.3way 0 0 Similarity/anthonymy/unrelatedness between verbs
WikiPedia BIU1.2way -0.0100 Lexical rules extracted from Wikipedia definition sentences, title parenthesis, redirect and hyperlink relations
WikiPedia cswhu1.3way 0.0133 0.0334 Lexical semantic rules
WikiPedia FBKirst1.2way 0.0100 Rules extracted from WP using Latent Semantic Analysis (LSA)
WikiPedia UAIC20091.3way 0.0117 0.0150 Relations between named entities
Wikipedia +
NER's (LingPipe, GATE) +
Perl patterns
UAIC20091.3way 0.0617 0.0500 NE module: NERs, in order to identify Persons, Locations, Jobs, Languages, etc; Perl patterns built by us for RTE4 in order to identify numbers and dates; our own resources extracted from Wikipedia in order to identify a "distance" between one name entity from hypothesis and name entities from text
WordNet AUEBNLP1.3way -0.0200 -0.0267 Synonyms
WordNet BIU1.2way 0.0250 Synonyms, hyponyms (2 levels away from the original term), hyponym_instance and derivations
WordNet Boeing3.3way 0.0400 0.0567
WordNet DFKI1.3way -0.0017 0
WordNet DFKI2.3way 0.0016 0.0034
WordNet DFKI3.3way 0.0017 0.0017
WordNet DLSIUAES1.2way 0.0083 Similarity between lemmata, computed by WordNet-based metrics
WordNet DLSIUAES1.3way -0.0050 -0.0033 Similarity between lemmata, computed by WordNet-based metrics
WordNet JU_CSE_TAC1.2way 0.0034 WordNet based Unigram match
WordNet PeMoZa1.2way -0.0050 Derivational Morphology from WordNet
WordNet PeMoZa1.2way 0.0133 Verb Entailment from Wordnet
WordNet PeMoZa2.2way 0.0100 Derivational Morphology from WordNet
WordNet PeMoZa2.2way -0.0033 Verb Entailment from Wordnet
WordNet QUANTA1.2way -0.0017 We use several relations from wordnet, such as synonyms, hyponym, hypernym et al.
WordNet Sagan1.3way 0 -0.0083 The system is based on machine learning approach. The ablation test was obtained with 2 less features using WordNet in the training and testing steps.


WordNet Siel_093.3way 0.0034 -0.0017 Similarity between nouns using WN tool
WordNet ssl1.3way 0 0.0067 WordNet Analysis
WordNet UB.dmirg3.2way 0
WordNet UI_ccg1.2way 0.0400 word similarity == identity
WordNet +
FrameNet
UB.dmirg3.2way 0
WordNet +
VerbOcean
DFKI1.3way 0 0.0017
WordNet +
VerbOcean
DFKI2.3way 0.0050 0.0067
WordNet +
VerbOcean
DFKI3.3way 0.0017 0.0017
WordNet +
VerbOcean
UAIC20091.3way 0.0200 0.0150 Contradiction identification
WordNet +
VerbOcean +
DLSIUAES_negation_list
DLSIUAES1.2way 0.0066 Antonym relations between verbs (VO+WN); polarity based on negation terms (short list constructed by ourselves)
WordNet +
VerbOcean +
DLSIUAES_negation_list
DLSIUAES1.3way -0.0100 -0.0050 Antonym relations between verbs (VO+WN); polarity based on negation terms (short list constructed by ourselves)
WordNet +
XWordNet
UAIC20091.3way 0.0100 0.0133 Synonymy, hyponymy and hypernymy and eXtended WordNet relation