Timezone: »

Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
Yizhe Zhang · Michel Galley · Jianfeng Gao · Zhe Gan · Xiujun Li · Chris Brockett · Bill Dolan

Tue Dec 04 02:00 PM -- 04:00 PM (PST) @ Room 210 #94

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.

Author Information

Yizhe Zhang (Microsoft Research)
Michel Galley (Microsoft Research)
Jianfeng Gao (Microsoft Research, Redmond, WA)
Zhe Gan (Microsoft)
Xiujun Li (Microsoft Research Redmond)
Chris Brockett (Microsoft Research AI)
Bill Dolan (Microsoft)

More from the Same Authors