# Progressive Open-Domain Response Generation with Multiple Controllable Attributes

arXiv: https://arxiv.org/abs/2106.14614 · HTML: https://mlsanity.com/paper/2106.14614/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 7 Jun 2021.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://mlsanity.com/paper/1605.06069/) (2016)
- [Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory](https://mlsanity.com/paper/1704.01074/) (2017)
- [Challenges in Building Intelligent Open-domain Dialog Systems](https://mlsanity.com/paper/1905.05709/) (2019)
- [What makes a good conversation? How controllable attributes affect human judgments](https://mlsanity.com/paper/1902.08654/) (2019)
- [Neural Responding Machine for Short-Text Conversation](https://mlsanity.com/paper/1503.02364/) (2015)
- [Controlling Output Length in Neural Encoder-Decoders](https://mlsanity.com/paper/1609.09552/) (2016)
- [A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data](https://mlsanity.com/paper/1911.04700/) (2019)
- [MojiTalk: Generating Emotional Responses at Scale](https://mlsanity.com/paper/1711.04090/) (2017)
- [Long and Diverse Text Generation with Planning-based Hierarchical Variational Model](https://mlsanity.com/paper/1908.06605/) (2019)
- [Content preserving text generation with attribute controls](https://mlsanity.com/paper/1811.01135/) (2018)
- [HiGRU: Hierarchical Gated Recurrent Units for Utterance-level Emotion Recognition](https://mlsanity.com/paper/1904.04446/) (2019)
- [Hierarchical Recurrent Attention Network for Response Generation](https://mlsanity.com/paper/1701.07149/) (2017)
- [A Discrete CVAE for Response Generation on Short-Text Conversation](https://mlsanity.com/paper/1911.09845/) (2019)
- [Neural Response Generation with Meta-Words](https://mlsanity.com/paper/1906.06050/) (2019)
- [Fine-Grained Sentence Functions for Short-Text Conversation](https://mlsanity.com/paper/1907.10302/) (2019)

## Built on by (most cited first, 6 of 6)

- [Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey](https://mlsanity.com/paper/2310.17894/) (2023)
- [Local Explanation of Dialogue Response Generation](https://mlsanity.com/paper/2106.06528/) (2021)
- [Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2209.00654/) (2022)
- [A Unified One-Step Solution for Aspect Sentiment Quad Prediction](https://mlsanity.com/paper/2306.04152/) (2023)
- [A Diffusion Model for Event Skeleton Generation](https://mlsanity.com/paper/2305.17458/) (2023)
- [Can Language Models perform Abductive Commonsense Reasoning?](https://mlsanity.com/paper/2207.05155/) (2022)

## Abstract (arXiv)

It is desirable to include more controllable attributes to enhance the diversity of generated responses in open-domain dialogue systems. However, existing methods can generate responses with only one controllable attribute or lack a flexible way to generate them with multiple controllable attributes. In this paper, we propose a Progressively trained Hierarchical Encoder-Decoder (PHED) to tackle this task. More specifically, PHED deploys Conditional Variational AutoEncoder (CVAE) on Transformer to include one aspect of attributes at one stage. A vital characteristic of the CVAE is to separate the latent variables at each stage into two types: a global variable capturing the common semantic features and a specific variable absorbing the attribute information at that stage. PHED then couples the CVAE latent variables with the Transformer encoder and is trained by minimizing a newly derived ELBO and controlled losses to produce the next stage's input and produce responses as required. Finally, we conduct extensive evaluations to show that PHED significantly outperforms the state-of-the-art neural generation models and produces more diverse responses as expected.