Narrative Generation in the Wild: Methods from NaNoGenMo

Stegeren, Judith van; Theune, Mariët

doi:10.18653/v1/w19-3407

Cited by 9 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various authors have investigated ways to improve the coherence of generated texts, for example by using planning strategies [13,29], learning frameworks [12] and coherence metrics [19]. Some generation systems do not actually enforce coherence in their outputs, but only suggest it through their form or content to trick the reader [11,24].…”

Section: Neural Language Generationmentioning

confidence: 99%

Fine-tuning GPT-2 on annotated RPG quests for NPC dialogue generation

Stegeren

Myśliwiec

2021

The 16th International Conference on the Foundations of Digital Games (FDG) 2021

Self Cite

View full text Add to dashboard Cite

GPT-2, a neural language model trained on a large dataset of English web text, has been used in a variety of natural language generation tasks because of the language quality and coherence of its outputs. In order to investigate the usability of GPT-2 for text generation for video games, we fine-tuned GPT-2 on a corpus of video game quests and used this model to generate dialogue lines for questgiver NPCs in a role-playing game. We show that the model learned the structure of quests and NPC dialogue, and investigate how the temperature parameter influences the language quality and creativity of the output artifacts. We evaluated our approach with a crowdsource experiment in which human judges were asked to rate hand-written and generated quest texts on language quality, coherence and creativity. CCS CONCEPTS• Applied computing → Computer games; • Computing methodologies → Natural language generation.

show abstract

Section: Neural Language Generationmentioning

confidence: 99%

Fine-tuning GPT-2 on annotated RPG quests for NPC dialogue generation

Stegeren

Myśliwiec

2021

The 16th International Conference on the Foundations of Digital Games (FDG) 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, if at some point a protagonist opens a window to air the room and the antagonist enters the building through this open window later as the story unfolds, such 'window' could be regarded as a perfect example of Chekhov's Gun. Although there are several recent results in the areas of suspense generation Doust and Piwek (2017), narrative personalization Wang et al (2017), and generation of short context-based narratives Womack and Freeman (2019), generating long stories is still a challenge van Stegeren and Theune (2019). We believe that CGR could provide deep insights into further computational research of narrative structure and is a vital component for the generation of longer entertaining stories.…”

Section: Cgr Taskmentioning

confidence: 98%

Actionable Entities Recognition Benchmark for Interactive Fiction

Tikhonov¹,

P.²

2021

Preprint

View full text Add to dashboard Cite

Chekhov's gun is a dramatic principle stating that every element in a story must be necessary, and irrelevant elements should be removed. This paper presents a new natural language processing task -Chekhov's gun recognition or (CGR)recognition of entities that are pivotal for the development of the plot. Though similar to classical Named Entity Recognition (NER) it has profound differences and is crucial for the tasks of narrative processing, since Chekhov's guns have a profound impact on the causal relationship in a story. The paper presents a new benchmark dataset for the CGR task that includes 5550 descriptions with one or more Chekhov's Gun in each and validates the task on two more datasets available in the natural language processing (NLP) literature."One must never place a loaded rifle on the stage if it isn't going to go off. It's wrong to make promises you don't mean to keep." Chekhov in his letter to Lazarev.Preprint. Under review.

show abstract

“…While existing models can generate stories with good local coherence, generating long stories is challenging. Difficulties in coalescing individual phrases into coherent plots and in maintaining character consistency throughout the story lead to a rapid decrease in coherence as the output length increases (van Stegeren and Theune, 2019). Neural narrative generation combining story-writing with human collaboration in an interactive way improves both story quality and human engagement (Goldfarb-Tarrant et al, 2019).…”

Section: Narrative Generation / Story Tellingmentioning

confidence: 99%

Neural Language Generation: Formulation, Methods, and Evaluation

Garbacea,

Mei

2020

Preprint

View full text Add to dashboard Cite

Recent advances in neural network-based generative modeling have reignited the hopes in having computer systems capable of seamlessly conversing with humans and able to understand natural language. Neural architectures have been employed to generate text excerpts to various degrees of success, in a multitude of contexts and tasks that fulfil various user needs. Notably, high capacity deep learning models trained on large scale datasets demonstrate unparalleled abilities to learn patterns in the data even in the lack of explicit supervision signals, opening up a plethora of new possibilities regarding producing realistic and coherent texts. While the field of natural language generation is evolving rapidly, there are still many open challenges to address. In this survey we formally define and categorize the problem of natural language generation. We review particular application tasks that are instantiations of these general formulations, in which generating natural language is of practical importance. Next we include a comprehensive outline of methods and neural architectures employed for generating diverse texts. Nevertheless, there is no standard way to assess the quality of text produced by these generative models, which constitutes a serious bottleneck towards the progress of the field. To this end, we also review current approaches to evaluating natural language generation systems. We hope this survey will provide an informative overview of formulations, methods, and assessments of neural natural language generation.

show abstract

Narrative Generation in the Wild: Methods from NaNoGenMo

Cited by 9 publications

References 27 publications

Fine-tuning GPT-2 on annotated RPG quests for NPC dialogue generation

Fine-tuning GPT-2 on annotated RPG quests for NPC dialogue generation

Actionable Entities Recognition Benchmark for Interactive Fiction

Neural Language Generation: Formulation, Methods, and Evaluation

Contact Info

Product

Resources

About