PCNN+ATT

Reported on 6 benchmarks across 2 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing6 results

Relation ExtractiononNYT Corpus
P@10%
69.4
best: 92.3 (KGPOOL)
Relation ExtractiononNYT Corpus
P@30%
51.8
best: 86.7 (KGPOOL)
Relation ExtractiononNew York Times Corpus
P@10%
69.4
best: 92.3 (KGPOOL)
Relation ExtractiononNew York Times Corpus
P@30%
51.8
best: 86.7 (KGPOOL)
Relationship Extraction (Distant Supervised)onNew York Times Corpus
P@10%
69.4
best: 92.3 (KGPOOL)
Relationship Extraction (Distant Supervised)onNew York Times Corpus
P@30%
51.8
best: 86.7 (KGPOOL)