HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Discourse Parsing On Instructional Dt Instr

Metrics

Standard Parseval (Full)
Standard Parseval (Nuclearity)
Standard Parseval (Relation)
Standard Parseval (Span)

Results

Performance results of various models on this benchmark

Model Name
Standard Parseval (Full)
Standard Parseval (Nuclearity)
Standard Parseval (Relation)
Standard Parseval (Span)
Paper TitleRepository
Top-down (XLNet)40.255.247.074.3A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing
Bottom-up (DeBERTa)44.460.051.477.8A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing
Top-down (BERT)30.944.637.665.3A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing
Top-down (SpanBERT)36.754.542.773.7A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing
Top-down (DeBERTa)43.457.950.077.3A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing
Guz et al. (2020)-44.41-64.55Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining-
Bottom-up (SpanBERT)40.553.846.072.9A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing
Top-down (RoBERTa)41.556.148.775.7A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing
Bottom-up (BERT)32.946.339.566.6A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing
Guz et al. (2020) (pretrained)-46.59-65.41Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining-
Bottom-up (XLNet)40.756.447.473.6A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing
Bottom-up (RoBERTa)41.455.547.973.2A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing
0 of 12 row(s) selected.