Fig 1.
A comparative example from the EMPATHETIC DIALOGUES dataset compares the standard responses with the KEMP model responses.
Fig 2.
Representation of single-round dialogue and multi-round dialogue tasks.
Fig 3.
EMO_SA’s architecture diagram.
It is composed of an emotional context graph, an emotional context encoder, and an emotion-dependency decoder. Compared with the original KEMP model, we mainly added an emotion encoder of the same level as the KEMP encoder and a shared fusion decoder to the emotion-dependency decoder.
Fig 4.
Projection structure diagram.
Fig 5.
Association structure diagram.
Table 1.
Emotional category of Empathetic Dialogue dataset.
Fig 6.
A sample of the Empathetic Dialogue dataset.
Table 2.
Automatic evaluation of results.
Table 3.
Automatic evaluation results with different layer fusions.
Table 4.
Ablation study.
Table 5.
Case study of the generated responses by EMO_SA and the baselines.