Controllable Neural Story Plot Generation via Reinforcement Learning

By Pradyumna Tambwekar, Murtaza Dhuliawala, Animesh Mehta, Lara J. Martin, Brent Harrison, Mark O. Riedl. 2018

41 citations recorded by the source corpus.

Subfields: Natural Language Processing, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Geoffrey Irving
2. Jeff Wu
3. Damai Dai
4. Xu Sun
5. Nisan Stiennon
6. Andy Coenen
7. Julian R. Medina
8. Paul Christiano

In Reinforcement Learning

1. Geoffrey Irving
2. Sergey Levine
3. Paul Christiano
4. Dario Amodei
5. Jeff Wu
6. Damai Dai
7. Xu Sun
8. Julian R. Medina

Citations in the corpus

• Fine-Tuning Language Models from Human Preferences (2019, background): “…such as BLEU for translation (Ranzato et al., 2015; Wu et al., 2016), ROUGE for summarization (Ranzato et al., 2015; Paulus et al., 2017; Wu and Hu, 2018; Gao et al., 2019b), music theory-based rewards (Jaques et al., 2017), or event detectors for story generation (Tambwekar et al., 2018).”
• A Survey of the Usages of Deep Learning for Natural Language Processing (2020, methodology): “[217] used reinforcement learning to train a text generation model.”
• Wordcraft: Story Writing With Large Language Models (2022, background): “[32] introduce a reward scheme to enable control over the plot of a generated story.”
• Learning to Control the Fine-grained Sentiment for Story Ending Generation (2019, background): “Tambwekar et al. (2018) introduces a policy gradient learning approach to ensure that the model ends with a specific type of event given in advance.”