Table 1.
A preprocessing example for the sentence “If in certain cases, an antidepressant is considered necessary, it may be advisable to replace tamoxifen with anastrozole.”.
Table 2.
Statistics of DDIExtraction 2013 dataset.
Table 3.
Examples of filtering instance for defined rules (the mentioned entities are in italic).
Table 4.
Statistics of DDIs 2013 dataset before and after processing.
Fig 1.
Overview of the SubGE-DDI. This figure illustrates the work flow of the SubGE-DDI framework.
The SubGE-DDI framework consists of three key parts–subgraph information, text features and fusion part. The subgraph information section is shown in the figure and the text features section and fusion part is illustrted in (A).
Fig 2.
Other features fusion methods.
(B), (C) are candidate methods for Fig 1A. The purple rectangles represent the information from BKG.
Table 5.
Experimental setting.
Table 6.
Evaluation on SemEval-2013 Task 9 test set.
Table 7.
Five-fold cross-validation average F1 scores on SemEval-2013 Task 9 train set.
Fig 3.
ROC curve and PR curve on SemEval-2013 Task 9 test set, (A) ROC curve, (B) PR curve.
Table 8.
Comparisons of both micro-averaged and macro-averaged metrics on different parts.
Table 9.
Comparison of both micro-averaged and macro-averaged metrics on different features fusion methods.
Table 10.
Comparisons of both micro-averaged and macro-averaged metrics on different pre-trained language models.
Fig 4.
The effect of different loss functions on our model.
Fig 5.
(A): Confusion matrix without Normalization, (B): Confusion matrix with Normalization.
Table 11.
Case studies of our model.