Fig 1.
An example of ASTE.
Fig 2.
The overview of proposed method.
Fig 3.
The architecture of GCN.
Table 1.
An example of SenticNet.
Fig 4.
An example of BDTF.
Fig 5.
Correspondence between S tags, E tags, aspect terms, and opinion terms.
Table 2.
The detailed statistics of ASTE-Data-V1 and ASTE-Data-V2 datasets.
Table 3.
Experimental results on ASTE-Data-V2.
Table 4.
Experimental results on ASTE-Data-V1.
Table 5.
The results of ablation study on ASTE-Data-V2.
Fig 6.
The experimental results of ablation study on ASTE-Data-V2.
Fig 7.
The experimental results of different number of GCN layers.
Table 6.
Case study.
Table 7.
The comparison of training time,inference time, parameter counts and memory usage.
Table 8.
Experimental results of significance tests on ASTE-Data-V2.