HyperAI초신경

Slot Filling On Kilt T Rex

평가 지표

Accuracy
F1
KILT-AC
KILT-F1
R-Prec
Recall@5

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Accuracy
F1
KILT-AC
KILT-F1
R-Prec
Recall@5
Paper TitleRepository
multi-task small19.325.810.00.00.00.0--
Multi-task DPR0.00.00.00.069.4683.88--
KGI_184.3687.2469.1470.5874.3683.14--
BART45.0649.240.00.00.00.0--
RAG59.262.9623.1223.9428.6833.04--
MetaRAG78.6681.7161.8863.0966.3676.24--
GENRE0.17.670.046.6679.4285.33--
TABi0.00.00.00.081.989.36--
Sphere57.0261.460.00.00.00.0--
single ngram83.7286.5360.0861.7267.881.52--
JivBest0.022.040.00.00.00.0--
Re2G87.6889.9375.8477.0580.789.0Re2G: Retrieve, Rerank, Generate
KGI_0 (reupload)77.981.3155.5456.7959.770.38--
chriskuei0.00.00.00.079.9885.75--
Coop. DistilBert49.0454.6236.6839.5748.0851.86--
T5-base43.5650.610.00.00.00.0KILT: a Benchmark for Knowledge Intensive Language Tasks
BART + DPR59.1662.7611.1211.4113.2617.04--
10k53.961.7427.8432.3437.6240.07--
Wikipedia81.3484.4664.6466.6475.6487.57--
DensePhrases53.961.7427.8432.3437.6240.07Learning Dense Representations of Phrases at Scale
0 of 20 row(s) selected.