# Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators

arXiv: https://arxiv.org/abs/1805.08352 · HTML: https://mlsanity.com/paper/1805.08352/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2018.

## Built on by (most cited first, 14 of 14)

- [Shades of BLEU, Flavours of Success: The Case of MultiWOZ](https://mlsanity.com/paper/2106.05555/) (2021)
- [Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation](https://mlsanity.com/paper/2310.07397/) (2023)
- [Learning to Reason for Text Generation from Scientific Tables](https://mlsanity.com/paper/2104.08296/) (2021)
- [Controlling Personality Style in Dialogue with Zero-Shot Prompt-Based Learning](https://mlsanity.com/paper/2302.03848/) (2023)
- [GenNI: Human-AI Collaboration for Data-Backed Text Generation](https://mlsanity.com/paper/2110.10185/) (2021)
- [Towards Inter-character Relationship-driven Story Generation](https://mlsanity.com/paper/2211.00676/) (2022)
- [Style Control for Schema-Guided Natural Language Generation](https://mlsanity.com/paper/2109.12211/) (2021)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Speaker-Conditioned Hierarchical Modeling for Automated Speech Scoring](https://mlsanity.com/paper/2109.00928/) (2021)
- [COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation](https://mlsanity.com/paper/2210.15500/) (2022)
- [From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey](https://mlsanity.com/paper/2110.15871/) (2021)
- [A Survey of Personality, Persona, and Profile in Conversational Agents and Chatbots](https://mlsanity.com/paper/2401.00609/) (2023)
- [PsychAdapter: Adapting LLM Transformers to Reflect Traits, Personality and Mental Health](https://mlsanity.com/paper/2412.16882/) (2024)
- [Enhancing Task-Oriented Dialogues with Chitchat: a Comparative Study Based on Lexical Diversity and Divergence](https://mlsanity.com/paper/2311.14067/) (2023)

## Abstract (arXiv)

Natural language generators for task-oriented dialogue must effectively realize system dialogue actions and their associated semantics. In many applications, it is also desirable for generators to control the style of an utterance. To date, work on task-oriented neural generation has primarily focused on semantic fidelity rather than achieving stylistic goals, while work on style has been done in contexts where it is difficult to measure content preservation. Here we present three different sequence-to-sequence models and carefully test how well they disentangle content and style. We use a statistical generator, Personage, to synthesize a new corpus of over 88,000 restaurant domain utterances whose style varies according to models of personality, giving us total control over both the semantic content and the stylistic variation in the training data. We then vary the amount of explicit stylistic supervision given to the three models. We show that our most explicit model can simultaneously achieve high fidelity to both semantic and stylistic goals: this model adds a context vector of 36 stylistic parameters as input to the hidden state of the encoder at each time step, showing the benefits of explicit stylistic supervision, even when the amount of training data is large.