Dependency Parsing On Tweebank
Metrics
Labelled Attachment Score
Unlabeled Attachment Score
Results
Performance results of various models on this benchmark
Model Name | Labelled Attachment Score | Unlabeled Attachment Score | Paper Title | Repository |
|---|---|---|---|---|
| SuPar-BERTweet | 83.4 | 87.2 | Cross-Dialect Social Media Dependency Parsing for Social Scientific Entity Attribute Analysis | |
| spaCy-XLM-RoBERTa | 79.39 | 83.82 | Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysis | - |
| Ensemble (20) | 79.4 | 83.4 | Parsing Tweets into Universal Dependencies | - |
0 of 3 row(s) selected.