Deep Dungeons and Dragons: Learning Character-Action Interactions
            from Role-Playing Game Transcripts

Louis, Annie; Sutton, Charles

doi:10.18653/v1/n18-2111

Cited by 8 publications

(12 citation statements)

References 15 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rather than containing a single short prompt to start the story, our stories on average contain 14 narrator prompts per story, with 41 natural language annotations which describe character goals, attributes, and key items useful for conditioning story generation models. 4 Like STORIUM, the stories in roleplayerguild (Louis and Sutton, 2018) are also formed from collaborative storytelling turns via a role-playing game, though this dataset lacks any prompts or annotations. Finally, datasets consisting of novels and other fiction, like PG-19 (Rae et al, 2020), provide long-form narratives without explicit structure to constrain generation.…”

Section: Storium: Gamified Storytellingmentioning

confidence: 99%

STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation

Akoury¹,

Shu-fan²,

Whiting³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Systems for story generation are asked to produce plausible and enjoyable stories given an input context. This task is underspecified, as a vast number of diverse stories can originate from a single input. The large output space makes it difficult to build and evaluate story generation models, as (1) existing datasets lack rich enough contexts to meaningfully guide models, and (2) existing evaluations (both crowdsourced and automatic) are unreliable for assessing long-form creative text. To address these issues, we introduce a dataset and evaluation platform built from STORIUM, an online collaborative storytelling community. Our author-generated dataset contains 6K lengthy stories (125M tokens) with fine-grained natural language annotations (e.g., character goals and attributes) interspersed throughout each narrative, forming a robust source for guiding models. We evaluate language models fine-tuned on our dataset by integrating them onto STORIUM, where real authors can query a model for suggested story continuations and then edit them. Automatic metrics computed over these edits correlate well with both user ratings of generated stories and qualitative feedback from semi-structured user interviews. We release both the STORIUM dataset and evaluation platform to spur more principled research into story generation.

show abstract

Section: Storium: Gamified Storytellingmentioning

confidence: 99%

STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation

Akoury¹,

Shu-fan²,

Whiting³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…The former consists of artificial five-sentence stories regarding everyday events, while the latter contains fictional stories of 1k words paired with short prompts. Besides, some recent works collected extra-long stories such as roleplayerguild (Louis and Sutton, 2018), PG-19 (Rae et al, 2020), and STORIUM (Akoury et al, 2020). Guan et al (2022) proposed a collection of Chinese stories.…”

Section: Related Workmentioning

confidence: 99%

A Corpus for Understanding and Generating Moral Stories

Guan¹,

Liu²,

Huang³

2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Teaching morals is one of the most important purposes of storytelling. An essential ability for understanding and writing moral stories is bridging story plots and implied morals. Its challenges mainly lie in: (1) grasping knowledge about abstract concepts in morals, (2) capturing inter-event discourse relations in stories, and (3) aligning value preferences of stories and morals concerning good or bad behavior. In this paper, we propose two understanding tasks and two generation tasks to assess these abilities of machines. We present STORAL, a new dataset of Chinese and English human-written moral stories. We show the difficulty of the proposed tasks by testing various models with automatic and manual evaluation on STORAL. Furthermore, we present a retrieval-augmented algorithm that effectively exploits related concepts or events in training sets as additional guidance to improve performance on these tasks.

show abstract

“…Work on individual entities -the kinds of entities proper names refer to -in computational linguistics and NLP has often made use of nov-els. However, such approaches have concentrated mainly on conceptually different tasks: learning character types (Bamman et al, 2013, Flekova andGurevych, 2015), inferring characters' features (Louis and Sutton, 2018), relations (Iyyer et al, 2016, Elson et al, 2010), networks (Labatut and Bost, 2019 or on broader natural language understanding tasks (Frermann et al, 2018), such as inferring plot structure (Elsner, 2012). Here, instead, the focus is on the investigation of the semantic and referential distinction between proper names and common nouns, whose distinct categorical status is a solid cross-linguistic phenomenon (Van Langendonck and Van de Velde, 2016).…”

Section: Characters In Novelsmentioning

confidence: 99%

Novel Aficionados and Doppelgängers: a referential task for semantic representations of individual entities

Bruera,

Herbelot

2021

Preprint

View full text Add to dashboard Cite

In human semantic cognition, proper names (names which refer to individual entities) are harder to learn and retrieve than common nouns. This seems to be the case for machine learning algorithms too, but the linguistic and distributional reasons for this behaviour have not been investigated in depth so far. To tackle this issue, we show that the semantic distinction between proper names and common nouns is reflected in their linguistic distributions by employing an original task for distributional semantics, the Doppelgänger test, an extensive set of models, and a new dataset, the Novel Aficionados dataset. The results indicate that the distributional representations of different individual entities are less clearly distinguishable from each other than those of common nouns, an outcome which intriguingly mirrors human cognition.

show abstract

Deep Dungeons and Dragons: Learning Character-Action Interactions from Role-Playing Game Transcripts

Cited by 8 publications

References 15 publications

STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation

STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation

A Corpus for Understanding and Generating Moral Stories

Novel Aficionados and Doppelgängers: a referential task for semantic representations of individual entities

Contact Info

Product

Resources

About