# Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation

arXiv: https://arxiv.org/abs/1712.02250 · HTML: https://mlsanity.com/paper/1712.02250/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2017.

## Built on by (most cited first, 12 of 12)

- [f-Divergence Minimization for Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/2307.15190/) (2023)
- [An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation](https://mlsanity.com/paper/2209.14627/) (2022)
- [Knowledge-enhanced Memory Model for Emotional Support Conversation](https://mlsanity.com/paper/2310.07700/) (2023)
- [PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism](https://mlsanity.com/paper/2212.09086/) (2022)
- [Ensemble Distillation for Unsupervised Constituency Parsing](https://mlsanity.com/paper/2310.01717/) (2023)
- [LLMR: Knowledge Distillation with a Large Language Model-Induced Reward](https://mlsanity.com/paper/2409.12500/) (2024)
- [KETCHUP: K-Step Return Estimation for Sequential Knowledge Distillation](https://mlsanity.com/paper/2504.19024/) (2025)
- [EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translation](https://mlsanity.com/paper/2403.00144/) (2024)
- [Towards Controlled and Diverse Generation of Article Comments](https://mlsanity.com/paper/2107.11781/) (2021)
- [Should we tweet this? Generative response modeling for predicting reception of public health messaging on Twitter](https://mlsanity.com/paper/2204.04353/) (2022)
- [SirenPose: Dynamic Scene Reconstruction via Geometric Supervision](https://mlsanity.com/paper/2512.20531/) (2025)
- [Learning Dynamic Scene Reconstruction with Sinusoidal Geometric Priors](https://mlsanity.com/paper/2512.22295/) (2025)

## Abstract (arXiv)

This paper addresses the question: Why do neural dialog systems generate short and meaningless replies? We conjecture that, in a dialog system, an utterance may have multiple equally plausible replies, causing the deficiency of neural networks in the dialog application. We propose a systematic way to mimic the dialog scenario in a machine translation system, and manage to reproduce the phenomenon of generating short and less meaningful sentences in the translation setting, showing evidence of our conjecture.