# Generating Diverse Story Continuations with Controllable Semantics

arXiv: https://arxiv.org/abs/1909.13434 · HTML: https://mlsanity.com/paper/1909.13434/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2019.

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

- [The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation](https://mlsanity.com/paper/2109.06835/) (2021)
- [Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech](https://mlsanity.com/paper/2106.01625/) (2021)
- [Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2401.05054/) (2024)
- [Changing the Mind of Transformers for Topically-Controllable Language Generation](https://mlsanity.com/paper/2103.15335/) (2021)
- ["What makes a question inquisitive?" A Study on Type-Controlled Inquisitive Question Generation](https://mlsanity.com/paper/2205.08056/) (2022)
- [Controlled Language Generation for Language Learning Items](https://mlsanity.com/paper/2211.15731/) (2022)
- [CLUE: Concept-Level Uncertainty Estimation for Large Language Models](https://mlsanity.com/paper/2409.03021/) (2024)
- [A survey of diversity quantification in natural language processing: The why, what, where and how](https://mlsanity.com/paper/2507.20858/) (2025)
- [An Ion Exchange Mechanism Inspired Story Ending Generator for Different Characters](https://mlsanity.com/paper/2209.00200/) (2022)

## Abstract (arXiv)

We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs. We focus on the setting of generating the next sentence of a story given its context. As controllable dimensions, we consider several sentence attributes, including sentiment, length, predicates, frames, and automatically-induced clusters. Our empirical results demonstrate: (1) our framework is accurate in terms of generating outputs that match the target control values; (2) our model yields increased maximum metric scores compared to standard n-best list generation via beam search; (3) controlling generation with semantic frames leads to a stronger combination of diversity and quality than other control variables as measured by automatic metrics. We also conduct a human evaluation to assess the utility of providing multiple suggestions for creative writing, demonstrating promising results for the potential of controllable, diverse generation in a collaborative writing system.