Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation

Zhiling Zhang, Mengyue Wu, Kenny Q. Zhu

Submission Type: Regular Long Paper

Submission Track: Dialogue and Interactive Systems

Submission Track 2: Natural Language Generation

Keywords: dialogue response generation, chatbot, controllable generation, multi-attributes

Abstract:

Controlling chatbot utterance generation with multiple attributes such as
personalities, emotions and dialogue acts is a practically useful but
under-studied problem.
We propose a novel framework called DASC
that possesses strong controllability with a weighted decoding paradigm,
while improving generation quality with the grounding in an
attribute semantics space. Generation with multiple attributes is then
intuitively implemented with an interpolation of multiple attribute embeddings,
which results in substantial reduction in the model sizes.
Experiments show that DASC can achieve high control accuracy
in generation task with the simultaneous control of 3 aspects while also producing interesting and
reasonably sensible responses, even in an out-of-distribution robustness
test.

Submission Number: 2460