Keyphrase Generation on KPTimes (test) benchmark leaderboard · SOTA2 Research

Keyphrase Generation on KPTimes (test)

78.4Semantic Precision (SemP)SciBERT-G

Evaluation Results

Method	Links
SciBERT-G2023.03		78.4	73.7	74.9	71.6	6.4	0.208	57.9	46.8
SciBART-large+OAGKX2023.03		78.2	76.6	76.3	71.8	6.9	0.203	58.1	47.2
BART-large2023.03		76.8	79.6	77	70.6	7.4	0.203	58.2	46.9
KeyBART2023.03		75.1	80.7	76.6	69.6	8.6	0.206	57.9	46.6
BERT+CRF2023.03		74.1	45.9	55	76.9	7.2	0.556	58.3	47.8
ExHiRD-h2023.03		72.5	71.3	70.9	68	14.9	0.238	57.2	45.4
CatSeq2023.03		72.3	71.4	70.8	68.3	19.1	0.257	56.9	45.4
Transformer2023.03		72	73.6	71.7	65.8	13.3	0.231	56.9	45.6
SetTrans2023.03		66.2	80.1	71.6	64.5	21	0.232	57.2	45.4
text-davinci-0032023.03		54.9	64.3	58.2	72.5	4.4	0.188	59	47.9
HyperMatch2023.03		49.3	65.5	55.4	70.3	12.4	0.271	58.7	47.7
TextRank2023.03		45.7	53.2	48.3	66.7	37.1	0.246	59.8	48.5
PromptRank2023.03		42.7	57.4	48.3	69.9	23.3	0.134	56.9	45.8
Kea2023.03		42.7	57.5	48.4	69.9	21.9	0.175	60.7	50
MultipartiteRank2023.03		41	57.5	47.2	67	12.3	0.15	58.9	48.3
TF-IDF2023.03		40.3	55.7	46.1	65.8	17.5	0.163	58.9	48.2
YAKE!2023.03		38.7	44.2	40.5	63.9	31.7	0.225	56.4	44.1
text-davinci-0032023.03		38.3	62	46.7	69	8.2	0.137	59.9	48.7
Azure Cognitive Services2023.03		31.2	42.5	35.5	72.8	14	0.133	54.3	42.5
RAKE2023.03		28.4	38	32.1	69.3	15.7	0.14	55.5	44.2
Amazon Comprehend2023.03		25.8	34.7	29.2	61.7	29.1	0.203	54.4	43.3