Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization

Explore this paper's citation graph

Summary

Adversarial Information Maximization (AIM), an adversarial learning framework that addresses informativeness and diversity, and explicitly optimizes a variational lower bound on pairwise mutual information between query and response.

Type
article
Published
2018-09-16
Cited by
319
References
47
Access
Open access

Keywords

Adversarial system, Maximization, Leverage (statistics), Computer science, Pairwise comparison

References

Cited by

Related papers