spaCy-XLM-RoBERTa

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Dependency ParsingonTweebank
Unlabeled Attachment Score· 2022-01-18
83.82
best: 87.2 (SuPar-BERTweet)
SOTA
Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysis arXiv:2201.07281
Dependency ParsingonTweebank
Labelled Attachment Score· 2022-01-18
79.39
best: 83.4 (SuPar-BERTweet)
Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysis arXiv:2201.07281