Difference between revisions of "WordNet - RTE Users"
Jump to navigation
Jump to search
m |
|||
| Line 11: | Line 11: | ||
| RTE3 | | RTE3 | ||
| 3.0 | | 3.0 | ||
| − | | Semantic relation between words | + | | Semantic relation between words |
| − | | | + | | No evaluation of the resource |
| + | |- bgcolor="#ECECEC" align="left" | ||
| + | | AUEB | ||
| + | | RTE3 | ||
| + | | 2.1 | ||
| + | | Synonymy resolution | ||
| + | | Replacing the words of H with their synonyms in T: on RTE3 data sets 2% improvement | ||
|- bgcolor="#ECECEC" align="left" | |- bgcolor="#ECECEC" align="left" | ||
| Boeing | | Boeing | ||
| RTE4 | | RTE4 | ||
| 2.0 | | 2.0 | ||
| − | | Semantic relation between words | + | | Semantic relation between words |
| No formal evaluation. Plays a role in most entailments found. | | No formal evaluation. Plays a role in most entailments found. | ||
| + | |- bgcolor="#ECECEC" align="left" | ||
| + | | DFKI | ||
| + | | RTE4 | ||
| + | | 3.0 | ||
| + | | Semantic relation between words | ||
| + | | No separate evaluation | ||
| + | |- bgcolor="#ECECEC" align="left" | ||
| + | | CERES | ||
| + | | RTE4 | ||
| + | | 3.0 | ||
| + | | Hypernyms, antonyms, indexWords(N,V,Adj,Adv) | ||
| + | | Used, but no evaluation performed | ||
| + | |- bgcolor="#ECECEC" align="left" | ||
| + | | Cambridge | ||
| + | | RTE4 | ||
| + | | 3.0 | ||
| + | | Meaning postulates from WordNet noun hyponymy, e.g. forall x: cat(x) -> animal(x) | ||
| + | | No systematic evaluation | ||
| + | |- bgcolor="#ECECEC" align="left" | ||
| + | | BIU | ||
| + | | RTE4 | ||
| + | | 3.0 | ||
| + | | Derived on the fly lexical entailment rules, using synonyms, hypernyms (up to two levels) and derivations. Also used as part of our novel lexical-syntactic resource | ||
| + | | 0.8% improvement in ablation test on RTE-4. Potential contribution is higher since this resource partially overlaps with the novel lexical syntactic rule base | ||
| + | |- bgcolor="#ECECEC" align="left" | ||
| + | | FbkIrst | ||
| + | | RTE4 | ||
| + | | 3.0 | ||
| + | | Lexical similarity | ||
| + | | No precise evaluation of the resource has been carried out. In our second run we used a combined system (EDITSneg + EDITSallbutneg), and we had an improvement of 0.6% in accuracy with respect to the first run in which only EDITSneg was used. EDITSallbutneg exploits lexical similarity (WordNet similarity), but we can’t affirm with precision that the improvement is due only to the use of WordNet | ||
| + | |- bgcolor="#ECECEC" align="left" | ||
| + | | | ||
| + | | | ||
| + | | | ||
| + | | | ||
| + | | | ||
| + | |- bgcolor="#ECECEC" align="left" | ||
| + | | | ||
| + | | | ||
| + | | | ||
| + | | | ||
| + | | | ||
|} | |} | ||
{|class="wikitable" cellpadding="3" cellspacing="0" border="0" style="margin-left: 20px;" | {|class="wikitable" cellpadding="3" cellspacing="0" border="0" style="margin-left: 20px;" | ||
|- | |- | ||
| − | ! align="left"|Total: | + | ! align="left"|Total: 8 |
|} | |} | ||
Revision as of 04:29, 6 April 2009
| Partecipants | Campaign | Version | Specific usage description | Evalutations / Comments |
|---|---|---|---|---|
| Del Monte | RTE3 | 3.0 | Semantic relation between words | No evaluation of the resource |
| AUEB | RTE3 | 2.1 | Synonymy resolution | Replacing the words of H with their synonyms in T: on RTE3 data sets 2% improvement |
| Boeing | RTE4 | 2.0 | Semantic relation between words | No formal evaluation. Plays a role in most entailments found. |
| DFKI | RTE4 | 3.0 | Semantic relation between words | No separate evaluation |
| CERES | RTE4 | 3.0 | Hypernyms, antonyms, indexWords(N,V,Adj,Adv) | Used, but no evaluation performed |
| Cambridge | RTE4 | 3.0 | Meaning postulates from WordNet noun hyponymy, e.g. forall x: cat(x) -> animal(x) | No systematic evaluation |
| BIU | RTE4 | 3.0 | Derived on the fly lexical entailment rules, using synonyms, hypernyms (up to two levels) and derivations. Also used as part of our novel lexical-syntactic resource | 0.8% improvement in ablation test on RTE-4. Potential contribution is higher since this resource partially overlaps with the novel lexical syntactic rule base |
| FbkIrst | RTE4 | 3.0 | Lexical similarity | No precise evaluation of the resource has been carried out. In our second run we used a combined system (EDITSneg + EDITSallbutneg), and we had an improvement of 0.6% in accuracy with respect to the first run in which only EDITSneg was used. EDITSallbutneg exploits lexical similarity (WordNet similarity), but we can’t affirm with precision that the improvement is due only to the use of WordNet |
| Total: 8 |
|---|