Table 4 Overview of systems which aimed at full coverage. The most frequent sense was used as the baseline method. We represent the results of Xu et al by using MeSH codes in the second row for the sake of comparability. The results of a C4.5 decision tree using the MeSH features are present in the third row. The systems of the two last rows first apply the combined co-author graph based heuristics and when they cannot decide they use the supervised prediction of the cosine similarity metric or the decision tree.
From: The strength of co-authorship in gene name disambiguation
Method | Human | Mouse | Fly | Yeast |
|---|---|---|---|---|
Baseline | 59.3%–99.1% | 79% | 66.7% | 65.5% |
Xu et al [14, 15] MeSH | 86.3%–94.4% | 90.7%–99.4% | 69.4%–99.7% | 78.9%–98.4% |
Decision tree | 84.68%–100% | 90.90%–99.84% | 72.53%–99.85% | 74.49%–100% |
Co-author heuristics + similarity | 91.87%–99.19% | 98.54%–99.75% | 97.20%–100% | 94.15%–99.70% |
Co-author heuristics + decision tree | 94.35%–100% | 98.85%–99.91% | 96.05%–99.85% | 99.63%–100% |