Guz et al. (2020)

Reported on 4 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 Processing5 results

Discourse ParsingonRST-DT
Standard Parseval (Nuclearity)· 2020-11-06
61.38
best: 70.4 (Bottom-up Llama 2 (70B))
Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining arXiv:2011.03203
Discourse ParsingonInstructional-DT (Instr-DT)
Standard Parseval (Nuclearity)· 2020-11-06
44.41
best: 60 (Bottom-up (DeBERTa))
Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining arXiv:2011.03203
Discourse ParsingonInstructional-DT (Instr-DT)
Standard Parseval (Span)· 2020-11-06
64.55
best: 77.8 (Bottom-up (DeBERTa))
Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining arXiv:2011.03203
Discourse ParsingonRST-DT
Standard Parseval (Span)
72.43
best: 79.8 (Bottom-up Llama 2 (70B))
Discourse ParsingonRST-DT
Standard Parseval (Span)
72.43
best: 79.8 (Bottom-up Llama 2 (70B))