Discourse Parsing on RST-DT

Metric: Standard Parseval (Relation) (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Standard Parseval (Relation)▼	Extra Data	Paper	Date↕	Code
1	Bottom-up Llama 2 (70B)	60	No	Can we obtain significant success in RST discour...	2024-03-08	Code
2	Bottom-up Llama 2 (13B)	57.8	No	Can we obtain significant success in RST discour...	2024-03-08	Code
3	Top-down Llama 2 (70B)	57.7	No	Can we obtain significant success in RST discour...	2024-03-08	Code
4	Top-down Llama 2 (13B)	57.7	No	Can we obtain significant success in RST discour...	2024-03-08	Code
5	Bottom-up Llama 2 (7B)	57.6	No	Can we obtain significant success in RST discour...	2024-03-08	Code
6	Top-down (XLNet)	57	No	A Simple and Strong Baseline for End-to-End Neur...	2022-10-15	Code
7	Top-down (DeBERTa)	56.6	No	A Simple and Strong Baseline for End-to-End Neur...	2022-10-15	Code
8	Bottom-up (XLNet)	56.3	No	A Simple and Strong Baseline for End-to-End Neur...	2022-10-15	Code
9	Top-down (RoBERTa)	55.8	No	A Simple and Strong Baseline for End-to-End Neur...	2022-10-15	Code
10	Bottom-up (RoBERTa)	55.4	No	A Simple and Strong Baseline for End-to-End Neur...	2022-10-15	Code
11	Top-down Llama 2 (7B)	55.2	No	Can we obtain significant success in RST discour...	2024-03-08	Code
12	Bottom-up (SpanBERT)	54.9	No	A Simple and Strong Baseline for End-to-End Neur...	2022-10-15	Code
13	Top-down (SpanBERT)	54.5	No	A Simple and Strong Baseline for End-to-End Neur...	2022-10-15	Code
14	End-to-end Top-down (XLNet)	51.6	No	RST Parsing from Scratch	2021-05-23	Code
15	DMRST (2021) + Cross-translation	51.6	Yes	DMRST: A Joint Framework for Document-Level Mult...	2021-10-09	Code
16	LSTM Dynamic	51.5	No	Top-down Discourse Parsing via Sequence Labelling	2021-02-03	Code
17	Transformer (static)	50.6	No	Top-down Discourse Parsing via Sequence Labelling	2021-02-03	Code
18	LSTM Static	50.5	No	Top-down Discourse Parsing via Sequence Labelling	2021-02-03	Code
19	DMRST (2021)	49.4	No	DMRST: A Joint Framework for Document-Level Mult...	2021-10-09	Code
20	Top-down (BERT)	48.3	No	A Simple and Strong Baseline for End-to-End Neur...	2022-10-15	Code
21	Bottom-up (BERT)	47.8	No	A Simple and Strong Baseline for End-to-End Neur...	2022-10-15	Code
22	Nguyen et al. (2021)	47.8	No	RST Parsing from Scratch	2021-05-23	Code
23	End-to-end Top-down (Glove)	47.7	No	RST Parsing from Scratch	2021-05-23	Code

#1Bottom-up Llama 2 (70B)SOTA
60
Standard Parseval (Relation)· 2024-03-08
Can we obtain significant success in RST discourse parsing by using Large Language Models?Code
#2Bottom-up Llama 2 (13B)
57.8
Standard Parseval (Relation)· 2024-03-08
Can we obtain significant success in RST discourse parsing by using Large Language Models?Code
#3Top-down Llama 2 (70B)
57.7
Standard Parseval (Relation)· 2024-03-08
Can we obtain significant success in RST discourse parsing by using Large Language Models?Code
#4Top-down Llama 2 (13B)
57.7
Standard Parseval (Relation)· 2024-03-08
Can we obtain significant success in RST discourse parsing by using Large Language Models?Code
#5Bottom-up Llama 2 (7B)
57.6
Standard Parseval (Relation)· 2024-03-08
Can we obtain significant success in RST discourse parsing by using Large Language Models?Code
#6Top-down (XLNet)SOTA
57
Standard Parseval (Relation)· 2022-10-15
A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing Code
#7Top-down (DeBERTa)
56.6
Standard Parseval (Relation)· 2022-10-15
A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing Code
#8Bottom-up (XLNet)
56.3
Standard Parseval (Relation)· 2022-10-15
A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing Code
#9Top-down (RoBERTa)
55.8
Standard Parseval (Relation)· 2022-10-15
A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing Code
#10Bottom-up (RoBERTa)
55.4
Standard Parseval (Relation)· 2022-10-15
A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing Code
#11Top-down Llama 2 (7B)
55.2
Standard Parseval (Relation)· 2024-03-08
Can we obtain significant success in RST discourse parsing by using Large Language Models?Code
#12Bottom-up (SpanBERT)
54.9
Standard Parseval (Relation)· 2022-10-15
A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing Code
#13Top-down (SpanBERT)
54.5
Standard Parseval (Relation)· 2022-10-15
A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing Code
#14End-to-end Top-down (XLNet)SOTA
51.6
Standard Parseval (Relation)· 2021-05-23
RST Parsing from Scratch Code
#15DMRST (2021) + Cross-translation
51.6
Standard Parseval (Relation)· Extra Data· 2021-10-09
DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing Code
#16LSTM DynamicSOTA
51.5
Standard Parseval (Relation)· 2021-02-03
Top-down Discourse Parsing via Sequence Labelling Code
#17Transformer (static)
50.6
Standard Parseval (Relation)· 2021-02-03
Top-down Discourse Parsing via Sequence Labelling Code
#18LSTM Static
50.5
Standard Parseval (Relation)· 2021-02-03
Top-down Discourse Parsing via Sequence Labelling Code
#19DMRST (2021)
49.4
Standard Parseval (Relation)· 2021-10-09
DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing Code
#20Top-down (BERT)
48.3
Standard Parseval (Relation)· 2022-10-15
A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing Code
#21Bottom-up (BERT)
47.8
Standard Parseval (Relation)· 2022-10-15
A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing Code
#22Nguyen et al. (2021)
47.8
Standard Parseval (Relation)· 2021-05-23
RST Parsing from Scratch Code
#23End-to-end Top-down (Glove)
47.7
Standard Parseval (Relation)· 2021-05-23
RST Parsing from Scratch Code