Exposure bias poses a common challenge in numerous natural language
proc...
Multi-task learning has been widely applied in computational vision, nat...
With the development of deep learning, advanced dialogue generation meth...
Conditional variational models, using either continuous or discrete late...
Complex dialogue mappings (CDM), including one-to-many and many-to-one
m...
There is a growing interest in improving the conversational ability of m...
Generative dialogue models suffer badly from the generic response proble...
Pre-trained models have achieved excellent performance on the dialogue t...
Conditional Variational AutoEncoder (CVAE) effectively increases the
div...
Many existing conversation models that are based on the encoder-decoder
...
Neural dialogue models suffer from low-quality responses when interacted...
Human dialogues are scenario-based and appropriate responses generally r...
Collaborative learning has successfully applied knowledge transfer to gu...
Neural conversational models learn to generate responses by taking into
...
Kernel methods form a theoretically-grounded, powerful and versatile
fra...
Kernel methods form a powerful, versatile, and theoretically-grounded
un...
We present a general nonlinear Bayesian filter for high-dimensional stat...
With the development of MOOCs massive open online courses, increasingly ...
Low rank matrix factorisation is often used in recommender systems as a ...
Non-negative Matrix Factorisation (NMF) has been extensively used in mac...