XMolCap: Advancing Molecular Captioning through Multimodal Fusion and Explainable Graph Neural Networks
Open paper
Benchmark
Model
Rank
Results
molecule-captioning-on-l-m-24
XMolCap
#2
BLEU-2: 77.4
BLEU-4: 56.0
ROUGE-1: 78.9
ROUGE-2: 59.4
ROUGE-L: 56.8
…
molecule-captioning-on-chebi-20
XMolCap
#8
BLEU-2: 62.0
BLEU-4: 53.8
METEOR: 67.8
ROUGE-1: 53.9
ROUGE-2: 61.8
…
Rank counts only results with a code link.