# NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation

arXiv: https://arxiv.org/abs/1810.00671 · HTML: https://mlsanity.com/paper/1810.00671/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2018.

## Built on by (most cited first, 9 of 9)

- [On the Evaluation Metrics for Paraphrase Generation](https://mlsanity.com/paper/2202.08479/) (2022)
- [GTM: A Generative Triple-Wise Model for Conversational Question Generation](https://mlsanity.com/paper/2106.03635/) (2021)
- [Learning Fine-grained Fact-Article Correspondence in Legal Cases](https://mlsanity.com/paper/2104.10726/) (2021)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [Triangular Bidword Generation for Sponsored Search Auction](https://mlsanity.com/paper/2101.11349/) (2021)
- [The SelectGen Challenge: Finding the Best Training Samples for Few-Shot Neural Text Generation](https://mlsanity.com/paper/2108.06614/) (2021)
- [WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue](https://mlsanity.com/paper/2108.01487/) (2021)
- [Precognition in Task-oriented Dialogue Understanding: Posterior Regularization by Future Context](https://mlsanity.com/paper/2203.03244/) (2022)
- [Is Translation Helpful? An Empirical Analysis of Cross-Lingual Transfer in Low-Resource Dialog Generation](https://mlsanity.com/paper/2305.12480/) (2023)

## Abstract (arXiv)

Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems. Though highly efficient in learning the backbone of human-computer communications, they suffer from the problem of strongly favoring short generic responses. In this paper, we argue that a good response should smoothly connect both the preceding dialogue history and the following conversations. We strengthen this connection through mutual information maximization. To sidestep the non-differentiability of discrete natural language tokens, we introduce an auxiliary continuous code space and map such code space to a learnable prior distribution for generation purpose. Experiments on two dialogue datasets validate the effectiveness of our model, where the generated responses are closely related to the dialogue context and lead to more interactive conversations.