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

Table 1.

Benefits and limitations of some previous works in task-oriented response generation.

We also compare with our method.

More »

Table 1 Expand

Fig 1.

Illustrative example showing the working of the Bi-LSTM encoder-decoder model.

More »

Fig 1 Expand

Fig 2.

Illustration showing the working of Bi-LSTM based encoder-decoder model with copy mechanism.

More »

Fig 2 Expand

Fig 3.

Illustration showing the working of the BERT-LSTM model.

More »

Fig 3 Expand

Fig 4.

Illustration of the working of the BERT-LSTM model with copy-mechanism.

More »

Fig 4 Expand

Fig 5.

Illustration of the KG construction algorithm at work.

More »

Fig 5 Expand

Fig 6.

Flowchart showing the working of the response generation system.

First the input utterance is used to construct or update the knowledge graph. In the second step this knowledge-graph along with the current utterance is fed to our deep-learning model. Finally the model works on the input and generates an appropriate context relevant response.

More »

Fig 6 Expand

Table 2.

Detailed dataset description of each domain and the combined dataset.

More »

Table 2 Expand

Table 3.

Automatic evaluation results of different experiments in terms of BLEU, Perplexity (PPL), ROUGE-1, ROUGE-2 and ROUGE-L (rouge F-measures values are mentioned here).

More »

Table 3 Expand

Table 4.

Human evaluation results of different experiments in terms of Fluency (Gra), Adequacy (Con), Slot Consistency (SC) and Intent Relevance (IR).

More »

Table 4 Expand

Table 5.

Example outputs from different systems showing the effect of copy mechanism and KG triples on response generation.

More »

Table 5 Expand

Table 6.

Few examples of errors produced by different systems.

More »

Table 6 Expand