Transformer (dynamic)

Reported on 3 benchmarks across 1 task · 1 paper

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

Natural Language Processing3 results

Discourse ParsingonRST-DT
Standard Parseval (Full)· 2021-02-03
49.2
best: 58.1 (Bottom-up Llama 2 (70B))
Top-down Discourse Parsing via Sequence Labelling arXiv:2102.02080
Discourse ParsingonRST-DT
Standard Parseval (Nuclearity)· 2021-02-03
60.1
best: 70.4 (Bottom-up Llama 2 (70B))
Top-down Discourse Parsing via Sequence Labelling arXiv:2102.02080
Discourse ParsingonRST-DT
Standard Parseval (Span)· 2021-02-03
70.2
best: 79.8 (Bottom-up Llama 2 (70B))
Top-down Discourse Parsing via Sequence Labelling arXiv:2102.02080