Semantic Diversity in Dialogue with Natural Language Inference
This work addresses the issue of low response diversity for neural conversational agents, offering incremental improvements in measurement and generation methods.
The paper tackles the problem of generating diverse responses in chitchat dialogue by proposing a new metric using Natural Language Inference (NLI) to measure semantic diversity, showing that contradiction relations and model confidence achieve state-of-the-art results, and introducing a generation procedure that increases NLI Diversity by an average of 137%.
Generating diverse, interesting responses to chitchat conversations is a problem for neural conversational agents. This paper makes two substantial contributions to improving diversity in dialogue generation. First, we propose a novel metric which uses Natural Language Inference (NLI) to measure the semantic diversity of a set of model responses for a conversation. We evaluate this metric using an established framework (Tevet and Berant, 2021) and find strong evidence indicating NLI Diversity is correlated with semantic diversity. Specifically, we show that the contradiction relation is more useful than the neutral relation for measuring this diversity and that incorporating the NLI model's confidence achieves state-of-the-art results. Second, we demonstrate how to iteratively improve the semantic diversity of a sampled set of responses via a new generation procedure called Diversity Threshold Generation, which results in an average 137% increase in NLI Diversity compared to standard generation procedures.