Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

A sample chat transcript from the annotated dataset.

More »

Fig 1 Expand

Table 1.

Statistics of the developed dataset.

More »

Table 1 Expand

Table 2.

Sentiment label distribution across the annotated dataset.

More »

Table 2 Expand

Fig 2.

End-to-end framework for a two-level proposed hierarchical dialogue manager fused with sentiment (ss).

More »

Fig 2 Expand

Fig 3.

The architectural diagram of Intent Classifier (IC) module.

More »

Fig 3 Expand

Table 3.

Quantitative analysis of intent classification module.

More »

Table 3 Expand

Fig 4.

The architectural diagram of Slot-Filling (SF) module.

More »

Fig 4 Expand

Table 4.

Quantitative analysis of sentiment classification module.

More »

Table 4 Expand

Fig 5.

Learning curve of TR based policies during training for different algorithms.

More »

Fig 5 Expand

Fig 6.

Learning curve of various policies during training.

More »

Fig 6 Expand

Fig 7.

Performance of the VAs during testing with different measures: (a) User Satisfaction, (b) Avg. Turn.

More »

Fig 7 Expand

Table 5.

p-values reported by Welch’s t-test on comparing our proposed SR+TR model with other models.

More »

Table 5 Expand

Fig 8.

Performance of the VAs tested with human evaluators: (a) success rate based on binary marking schema, (b) Distribution of user-ratings based on variable marking schema for SR+TR.

More »

Fig 8 Expand

Fig 9.

Performance of the VAs during testing: (a) SR+TR, (b) TR.

More »

Fig 9 Expand

Table 6.

Quantitative analysis of slot-filling module.

More »

Table 6 Expand