We present a dialogue generation model that directly captures the variability in possible responses to a given input, which reduces the ‘boring output’ issue of deterministic dialogue models. Experiments show that our model generates more diverse outputs than baseline models, and also generates more consistently acceptable output than sampling from a deterministic encoder-decoder model
As the functionality of dialogue systems evolves, hybrid dialogue systems that accomplish user-speci...
Deep latent variable models is a class of models that parameterise components of probabilistic laten...
Dialogue promises a natural and effective method for users to interact with and obtain information f...
Neural conversational dialogue agents often produce uninteresting, broad responses, such as “Yes” or...
Conditional variational models, using either continuous or discrete latent variables, are powerful f...
Many sequence-to-sequence dialogue models tend to generate safe, uninformative responses. There have...
Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, th...
Sequential data often possesses hierarchical structures with complex dependencies between sub-sequen...
The generation of personalized dialogue is vital to natural and human-like conversation. Typically, ...
We aim to overcome the lack of diversity in responses of current dialogue systems and to develop a d...
The sequence-to-sequence model is a widely used model for dialogue response generators, but it tends...
In corpus-based response generation, dialogue utterances and strategies are constructed in the form ...
Dialogue systems are artefacts that converse with human users in order to achieve some task. Each st...
To the same utterance, people's responses in everyday dialogue may be diverse largely in terms of co...
Reinforcement techniques have been successfully used to maximise the expected cumulative reward of s...
As the functionality of dialogue systems evolves, hybrid dialogue systems that accomplish user-speci...
Deep latent variable models is a class of models that parameterise components of probabilistic laten...
Dialogue promises a natural and effective method for users to interact with and obtain information f...
Neural conversational dialogue agents often produce uninteresting, broad responses, such as “Yes” or...
Conditional variational models, using either continuous or discrete latent variables, are powerful f...
Many sequence-to-sequence dialogue models tend to generate safe, uninformative responses. There have...
Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, th...
Sequential data often possesses hierarchical structures with complex dependencies between sub-sequen...
The generation of personalized dialogue is vital to natural and human-like conversation. Typically, ...
We aim to overcome the lack of diversity in responses of current dialogue systems and to develop a d...
The sequence-to-sequence model is a widely used model for dialogue response generators, but it tends...
In corpus-based response generation, dialogue utterances and strategies are constructed in the form ...
Dialogue systems are artefacts that converse with human users in order to achieve some task. Each st...
To the same utterance, people's responses in everyday dialogue may be diverse largely in terms of co...
Reinforcement techniques have been successfully used to maximise the expected cumulative reward of s...
As the functionality of dialogue systems evolves, hybrid dialogue systems that accomplish user-speci...
Deep latent variable models is a class of models that parameterise components of probabilistic laten...
Dialogue promises a natural and effective method for users to interact with and obtain information f...