TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Bottom-up (SpanBERT)

Bottom-up (SpanBERT)

Reported on 7 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 Processing7 results

  • Discourse ParsingonRST-DT
    Standard Parseval (Full)· 2022-10-15
    52.7
    best: 58.1 (Bottom-up Llama 2 (70B))
    A Simple and Strong Baseline for End-to-End Neural RST-style Discourse ParsingarXiv:2210.08355
  • Discourse ParsingonRST-DT
    Standard Parseval (Nuclearity)· 2022-10-15
    65.3
    best: 70.4 (Bottom-up Llama 2 (70B))
    A Simple and Strong Baseline for End-to-End Neural RST-style Discourse ParsingarXiv:2210.08355
  • Discourse ParsingonRST-DT
    Standard Parseval (Relation)· 2022-10-15
    54.9
    best: 60 (Bottom-up Llama 2 (70B))
    A Simple and Strong Baseline for End-to-End Neural RST-style Discourse ParsingarXiv:2210.08355
  • Discourse ParsingonInstructional-DT (Instr-DT)
    Standard Parseval (Full)· 2022-10-15
    40.5
    best: 44.4 (Bottom-up (DeBERTa))
    A Simple and Strong Baseline for End-to-End Neural RST-style Discourse ParsingarXiv:2210.08355
  • Discourse ParsingonInstructional-DT (Instr-DT)
    Standard Parseval (Nuclearity)· 2022-10-15
    53.8
    best: 60 (Bottom-up (DeBERTa))
    A Simple and Strong Baseline for End-to-End Neural RST-style Discourse ParsingarXiv:2210.08355
  • Discourse ParsingonInstructional-DT (Instr-DT)
    Standard Parseval (Relation)· 2022-10-15
    46
    best: 51.4 (Bottom-up (DeBERTa))
    A Simple and Strong Baseline for End-to-End Neural RST-style Discourse ParsingarXiv:2210.08355
  • Discourse ParsingonInstructional-DT (Instr-DT)
    Standard Parseval (Span)· 2022-10-15
    72.9
    best: 77.8 (Bottom-up (DeBERTa))
    A Simple and Strong Baseline for End-to-End Neural RST-style Discourse ParsingarXiv:2210.08355