The edit can be undone. Please check the comparison below to verify that this is what you want to do, and then publish the changes below to finish undoing the edit.
| Latest revision | Your text | ||
| Line 1: | Line 1: | ||
| − | == OntoNotes 5.0 |
+ | == OntoNotes 5.0 == |
Using development and test set specified by [http://conll.cemantix.org/2012/introduction.html CoNLL-2012 Shared Task] (coreference resolution). |
Using development and test set specified by [http://conll.cemantix.org/2012/introduction.html CoNLL-2012 Shared Task] (coreference resolution). |
||
| Line 35: | Line 35: | ||
|Täckström et al. (2015)<ref name=":0" /> |
|Täckström et al. (2015)<ref name=":0" /> |
||
|Täckström et al. (2015)<ref name=":0" /> |
|Täckström et al. (2015)<ref name=":0" /> |
||
| − | |- |
||
| − | |Zhou and Xu (2015)<ref name=":1">Zhou, Jie, and Wei Xu. "End-to-end learning of semantic role labeling using recurrent neural networks." ''Proceedings of the Annual Meeting of the Association for Computational Linguistics''. 2015.</ref> |
||
| − | | |
||
| − | | |
||
| − | |81.27 |
||
| − | | |
||
| − | |Recurrent NN, no syntax |
||
| − | |Zhou and Xu (2015)<ref name=":1" /> |
||
| − | |Zhou and Xu (2015)<ref name=":1" /> |
||
| − | |- |
||
| − | | |
||
| − | | |
||
| − | | |
||
| − | | |
||
| − | | |
||
| − | | |
||
| − | | |
||
| − | | |
||
| − | |} |
||
| − | |||
| − | == CoNLL-2005 == |
||
| − | {| class="article-table" |
||
| − | !Model |
||
| − | !P |
||
| − | !R |
||
| − | !F1 |
||
| − | !Comp. |
||
| − | !Notes |
||
| − | !Performance ref. |
||
| − | !Model ref. |
||
| − | |- |
||
| − | |Zhou and Xu (2015)<ref name=":1" /> |
||
| − | | |
||
| − | | |
||
| − | |81.07 |
||
| − | | |
||
| − | |Recurrent NN, no syntax |
||
| − | |Zhou and Xu (2015)<ref name=":1" /> |
||
| − | |Zhou and Xu (2015)<ref name=":1" /> |
||
|- |
|- |
||
| |
| |
||