# SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks

arXiv: https://arxiv.org/abs/2109.01958 · HTML: https://mlsanity.com/paper/2109.01958/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 5 Sep 2021.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [The Second Conversational Intelligence Challenge (ConvAI2)](https://mlsanity.com/paper/1902.00098/) (2019)
- [PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable](https://mlsanity.com/paper/1910.07931/) (2019)
- [What makes a good conversation? How controllable attributes affect human judgments](https://mlsanity.com/paper/1902.08654/) (2019)
- [Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems](https://mlsanity.com/paper/1508.01745/) (2015)
- [Learning to Write with Cooperative Discriminators](https://mlsanity.com/paper/1805.06087/) (2018)
- [ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons](https://mlsanity.com/paper/1909.03087/) (2019)
- [The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents](https://mlsanity.com/paper/1911.03768/) (2019)
- [Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention](https://mlsanity.com/paper/1905.12866/) (2019)
- [Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints](https://mlsanity.com/paper/1809.01215/) (2018)
- [Plug-and-Play Conversational Models](https://mlsanity.com/paper/2010.04344/) (2020)
- [Adapting a Language Model for Controlled Affective Text Generation](https://mlsanity.com/paper/2011.04000/) (2020)

## Built on by (most cited first, 5 of 5)

- [Few-Shot Bot: Prompt-Based Learning for Dialogue Systems](https://mlsanity.com/paper/2110.08118/) (2021)
- [PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation](https://mlsanity.com/paper/2203.09100/) (2022)
- [Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation](https://mlsanity.com/paper/2306.10317/) (2023)
- [Attribute Controlled Dialogue Prompting](https://mlsanity.com/paper/2307.05228/) (2023)
- [Topic-switch adapted Japanese Dialogue System based on PLATO-2](https://mlsanity.com/paper/2302.11280/) (2023)

## Abstract (arXiv)

Transformer-based pre-trained language models boost the performance of open-domain dialogue systems. Prior works leverage Transformer-based pre-trained language models to generate texts with desired attributes in two general approaches: (1) gradient-based methods: updating all latent representations of pre-trained models with gradients from attribute models; (2) weighted-decoding methods: re-ranking beam candidates from pre-trained models with attribute functions. However, gradient-based methods lead to high computation cost and can easily get overfitted on small training sets, while weighted-decoding methods are inherently constrained by the low-variance high-bias pre-trained model. In this work, we propose a novel approach to control the generation of Transformer-based pre-trained language models: the SideControl framework, which leverages a novel control attributes loss to incorporate useful control signals, and is shown to perform well with very limited training samples. We evaluate our proposed method on two benchmark open-domain dialogue datasets, and results show that the SideControl framework has better controllability, higher generation quality and better sample-efficiency than existing gradient-based and weighted-decoding baselines.