paper-with-me

Slot Filling 벤치마크

Slot Filling on KILT: T-REx

20개 결과 · ⬇ CSV · JSON

KILT-AC

0 18.96 37.92 56.88 75.84 2020-09 2026-11 T5-base — 0.0 (2020-09-04) DensePhrases — 27.84 (2020-12-23) Re2G — 75.84 (2022-07-13) T5-base — 0.0 (2020-09-04) DensePhrases — 27.84 (2020-12-23) Re2G — 75.84 (2022-07-13)
RankModel KILT-ACR-PrecRecall@5AccuracyF1KILT-F1 PaperCodeYear
1 Re2G 75.8480.789.087.6889.9377.05 Re2G: Retrieve, Rerank, Generate ibm/kgi-slot-filling 2022
2 KGI_1 69.1474.3683.1484.3687.2470.58
3 Wikipedia 64.6475.6487.5781.3484.4666.64
4 MetaRAG 61.8866.3676.2478.6681.7163.09
5 single ngram 60.0867.881.5283.7286.5361.72
6 KGI_0 (reupload) 55.5459.770.3877.981.3156.79
7 Coop. DistilBert 36.6848.0851.8649.0454.6239.57
8 DensePhrases 27.8437.6240.0753.961.7432.34 Learning Dense Representations of Phrases at Scale princeton-nlp/SimCSE · jhyuklee/DensePhrases · princeton-nlp/DensePhrases · +1 2020
8 10k 27.8437.6240.0753.961.7432.34
10 RAG 23.1228.6833.0459.262.9623.94
11 BART + DPR 11.1213.2617.0459.1662.7611.41
12 GENRE 0.0479.4285.330.17.676.66
13 TABi 0.081.989.360.00.00.0
13 chriskuei 0.079.9885.750.00.00.0
13 Multi-task DPR 0.069.4683.880.00.00.0
13 Sphere 0.00.00.057.0261.460.0
13 BART 0.00.00.045.0649.240.0
13 T5-base 0.00.00.043.5650.610.0 KILT: a Benchmark for Knowledge Intensive Language Tasks facebookresearch/KILT · facebookresearch/editeval · zouharvi/kb-shrink 2020
13 multi-task small 0.00.00.019.325.810.0
13 JivBest 0.00.00.00.022.040.0
1–20 / 20 페이지당 10 20 50 100