Large pretrained language models can easily produce toxic or biased cont...
Conditional variational models, using either continuous or discrete late...
Complex dialogue mappings (CDM), including one-to-many and many-to-one
m...
Conversations are always related to certain topics. However, it is
chall...
Offensive language detection and prevention becomes increasing critical ...
The ability to quickly learn new knowledge (e.g. new classes or data
dis...
As the labeling cost for different modules in task-oriented dialog (ToD)...
Utterance-level intent detection and token-level slot filling are two ke...
Code representation learning, which aims to encode the semantics of sour...
Natural language generation (NLG) is an essential component of task-orie...
Session-based recommendation has received growing attention recently due...
Increasing concerns with privacy have stimulated interests in Session-ba...
Natural language generation (NLG) is an essential component of task-orie...
There has been growing interests in recent years from both practical and...
The main goal of modeling human conversation is to create agents which c...