Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization

Yizhe Zhang,Michel Galley,Jianfeng Gao,Zhe Gan,Xiujun Li,Chris Brockett,W. Dolan

Published 2018 in Neural Information Processing Systems

ABSTRACT

Responses generated by neural conversational models tend to lack informativeness and diversity. We present Adversarial Information Maximization (AIM), an adversarial learning framework that addresses these two related but distinct problems. To foster response diversity, we leverage adversarial training that allows distributional matching of synthetic and real responses. To improve informativeness, our framework explicitly optimizes a variational lower bound on pairwise mutual information between query and response. Empirical results from automatic and human evaluations demonstrate that our methods significantly boost informativeness and diversity.

PUBLICATION RECORD

  • Publication year

    2018

  • Venue

    Neural Information Processing Systems

  • Publication date

    2018-09-16

  • Fields of study

    Computer Science

  • Identifiers
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-46 of 46 references · Page 1 of 1

CITED BY

Showing 1-100 of 314 citing papers · Page 1 of 4