# Jointly Optimizing Diversity and Relevance in Neural Response Generation

arXiv: https://arxiv.org/abs/1902.11205 · HTML: https://mlsanity.com/paper/1902.11205/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2019.

## Built on by (most cited first, 22 of 22)

- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [Dialogue Response Ranking Training with Large-Scale Human Feedback Data](https://mlsanity.com/paper/2009.06978/) (2020)
- [Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech](https://mlsanity.com/paper/2106.01625/) (2021)
- [Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation](https://mlsanity.com/paper/2103.05271/) (2021)
- [Diversifying Dialog Generation via Adaptive Label Smoothing](https://mlsanity.com/paper/2105.14556/) (2021)
- [Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoders](https://mlsanity.com/paper/2106.03410/) (2021)
- [GTM: A Generative Triple-Wise Model for Conversational Question Generation](https://mlsanity.com/paper/2106.03635/) (2021)
- [Measuring and Improving Semantic Diversity of Dialogue Generation](https://mlsanity.com/paper/2210.05725/) (2022)
- [GePSAn: Generative Procedure Step Anticipation in Cooking Videos](https://mlsanity.com/paper/2310.08312/) (2023)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables](https://mlsanity.com/paper/2212.01145/) (2022)
- [A survey of diversity quantification in natural language processing: The why, what, where and how](https://mlsanity.com/paper/2507.20858/) (2025)
- [THINK: A Novel Conversation Model for Generating Grammatically Correct and Coherent Responses](https://mlsanity.com/paper/2105.13630/) (2021)
- [Stop Filtering: Multi-View Attribute-Enhanced Dialogue Learning](https://mlsanity.com/paper/2205.11206/) (2022)
- [Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games](https://mlsanity.com/paper/2304.07258/) (2023)
- [VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder](https://mlsanity.com/paper/2307.00852/) (2023)
- [Text Summarization with Oracle Expectation](https://mlsanity.com/paper/2209.12714/) (2022)
- [Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder](https://mlsanity.com/paper/2212.00231/) (2022)
- [Heterogeneous-Branch Collaborative Learning for Dialogue Generation](https://mlsanity.com/paper/2303.11621/) (2023)
- [Neural Conversation Models and How to Rein Them in: A Survey of Failures and Fixes](https://mlsanity.com/paper/2308.06095/) (2023)
- [Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey](https://mlsanity.com/paper/2411.09166/) (2024)
- [Guiding Topic Flows in the Generative Chatbot by Enhancing the ConceptNet with the Conversation Corpora](https://mlsanity.com/paper/2109.05406/) (2021)

## Abstract (arXiv)

Although recent neural conversation models have shown great potential, they often generate bland and generic responses. While various approaches have been explored to diversify the output of the conversation model, the improvement often comes at the cost of decreased relevance. In this paper, we propose a SpaceFusion model to jointly optimize diversity and relevance that essentially fuses the latent space of a sequence-to-sequence model and that of an autoencoder model by leveraging novel regularization terms. As a result, our approach induces a latent space in which the distance and direction from the predicted response vector roughly match the relevance and diversity, respectively. This property also lends itself well to an intuitive visualization of the latent space. Both automatic and human evaluation results demonstrate that the proposed approach brings significant improvement compared to strong baselines in both diversity and relevance.