Tham khảo tài liệu 'biomedical engineering trends research and technologies part 16', kỹ thuật - công nghệ, cơ khí - chế tạo máy phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | 590 Biomedical Engineering Trends Research and Technologies P R F OF AUC AUC SPT SPT Extension Dependency Dependency Extension SPT Dependency SPT Extension Dependency Extension Table 2. Effectiveness of SPT dependency tree and their extensions on Aimed Effectiveness of different kernels The performances of different kernels tested on Aimed are shown in Table 3. Among the four individual kernels the performance of the graph kernel is the best. As discussed in Section the reason is that the graph kernels can treat the parser s output and word features at the same time. The performance of the feature-based kernel ranks second since it uses protein names distance and Keyword feature besides words features otherwise with only words features its performance an F-score of and an AUC of is worse than that of the tree kernel . The performance of the tree kernel is almost the same with that of the feature-based kernel. P R F F AUC Feature-based kernel BOW Miwa Tree kernel Tree kernel Miwa Graph kernel Graph kernel Miwa Tree kernel Feature-based kernel Tree kernel BOW Miwa Graph kernel Feature-based kernel Graph kernel BOW Miwa Graph kernel Tree kernel Tree kernel Graph kernel Miwa Feature-based kernel 87. 83 Tree kernel Graph kernel Tree kernel Graph kernel BOW Miwa Table 3. Effectiveness of different kernels and performance comparison with those of Miwa s method on Aimed. The weights of each individual kernel in combined kernels are in the .
