Volume
OASIcs, Volume 45
6th Workshop on Computational Models of Narrative (CMN 2015)
- Part of: Series: Open Access Series in Informatics (OASIcs)
Event
CMN 2015, May 26-28, 2015, Atlanta, USAEditors
Publication Details
- published at: 2015-08-14
- Publisher: Schloss Dagstuhl – Leibniz-Zentrum für Informatik
- ISBN: 978-3-939897-93-4
- DBLP: db/conf/cmn/cmn2015
Access Numbers
- Detailed Access Statistics available here
-
Total Document Accesses (updated on a weekly basis):
0PDF Downloads
Documents
No documents found matching your filter selection.
Document
Complete Volume
OASIcs, Volume 45, CMN'15, Complete Volume
Abstract
OASIcs, Volume 45, CMN'15, Complete Volume
Cite as
6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@Proceedings{finlayson_et_al:OASIcs.CMN.2015,
title = {{OASIcs, Volume 45, CMN'15, Complete Volume}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015},
URN = {urn:nbn:de:0030-drops-53606},
doi = {10.4230/OASIcs.CMN.2015},
annote = {Keywords: Knowledge Representation Formalisms and Methods, Artificial Intelligence, General/Cognitive simulation, Natural Language Processing, Simulation and Modeling, Problem Solving, Control Methods, and Search, Distributed Artificial Intelligence, Psychology, Literature}
}
Document
Front Matter
Frontmatter, Table of Contents, Preface, List of Authors
Abstract
Welcome to the Sixth Workshop on Computational Models of Narrative. This year finds us co-located with the Third Annual Conference of Advanced in Cognitive Systems (CogSys 2015). This association made it appropriate to have a special focus on the intersection of cognitive systems and narrative. This intersection is rich and broad, covering the gamut from psychological and cognitive impact of narratives to our ability to model narrative responses computationally. Papers contributed to this volume tackle questions of narrative analysis in the domains of medical information and journalism, and of various story generation systems and frameworks. They look to extend prior paradigms, in one case connecting event segmentation theory to the computational modeling of narrative, and in another, proposing a model for synthesizing temporal, ontological, and psychological aspects of story. And they report on experiments such as the application of syntactic and semantic feature detection to the exploration of higher-level storytelling tropes such as romantic love and animacy.
Cite as
6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. i-x, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{finlayson_et_al:OASIcs.CMN.2015.i,
author = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
title = {{Frontmatter, Table of Contents, Preface, List of Authors}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {i--x},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.i},
URN = {urn:nbn:de:0030-drops-52759},
doi = {10.4230/OASIcs.CMN.2015.i},
annote = {Keywords: Frontmatter, Table of Contents, Preface, List of Authors}
}
Document
Invited Talk
Tell Me a Story: Toward More Expressive and Coherent Computational Narratives (Invited Talk)
Abstract
Since narrative is a foundational framework for the on-going co-evolution of human cognition and culture, the advent of computation as a new medium for representing narratives offers the promise of ratcheting up human understanding and expressive power, just as previous media of representation like language and writing have done. But digital representation often produces artifacts that are story-like but not really stories, leaving open the question of how we can make use of computational models of narrative to expand our capacity for shared meaning-making. I will address this problem by looking at the complementary strengths and weaknesses of simulation making, game design, and storytelling as cultural abstraction systems, and suggest some directions for incorporating richer story structures into research on computational narratives.
Cite as
Janet H. Murray. Tell Me a Story: Toward More Expressive and Coherent Computational Narratives (Invited Talk). In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, p. 1, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{murray:OASIcs.CMN.2015.1,
author = {Murray, Janet H.},
title = {{Tell Me a Story: Toward More Expressive and Coherent Computational Narratives}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {1--1},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.1},
URN = {urn:nbn:de:0030-drops-52742},
doi = {10.4230/OASIcs.CMN.2015.1},
annote = {Keywords: computational models of narrative}
}
Document
From Episodic Memory to Narrative in a Cognitive Architecture
Abstract
Human experiences are stored in episodic memory and are the basis for developing semantic narrative structures and many of the narratives we continually compose. Episodic memory has only recently been recognized as a necessary module in general cognitive architectures and little work has been done to examine how the data stored by these modules may be formulated as narrative structures. This paper regards episodic memory as fundamental to narrative intelligence and considers the gap between simple episodic memory representations and narrative structures, and proposes an approach to generating basic narratives from episodic sequences. An approach is outlined considering the Soar general cognitive architecture and Zacks’ Event Segmentation Theory.
Cite as
Tory S. Anderson. From Episodic Memory to Narrative in a Cognitive Architecture. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 2-11, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{anderson:OASIcs.CMN.2015.2,
author = {Anderson, Tory S.},
title = {{From Episodic Memory to Narrative in a Cognitive Architecture}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {2--11},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.2},
URN = {urn:nbn:de:0030-drops-52761},
doi = {10.4230/OASIcs.CMN.2015.2},
annote = {Keywords: Narrative, Episodic Memory, Cognitive Architecture, Event Segmentation}
}
Document
Optimal Eventfulness of Narratives
Abstract
This study examines whether there is an optimal degree of eventfulness of short narratives. We ask whether there is a specific degree of eventfulness (unexpectedness) that makes them "stick" better than other stories so that they are maintained more faithfully in serial reproduction (telephone games). The result is: probably not. The finding is that there is an impressive correlation of eventfulness rankings of original stories and resulting retellings in serial reproduction, despite the change of many other story elements and almost regardless of low or high eventfulness. Put more simply, people remember and retell “eventfulness” accurately, even when the actual events and circumstances of a story are changed.
Cite as
Fritz Breithaupt, Eleanor Brower, and Sarah Whaley. Optimal Eventfulness of Narratives. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 12-22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{breithaupt_et_al:OASIcs.CMN.2015.12,
author = {Breithaupt, Fritz and Brower, Eleanor and Whaley, Sarah},
title = {{Optimal Eventfulness of Narratives}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {12--22},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.12},
URN = {urn:nbn:de:0030-drops-52775},
doi = {10.4230/OASIcs.CMN.2015.12},
annote = {Keywords: Narrative, Event, Eventfulness, Event cognition; Serial reproduction; Linear and bounded iteration, Event memory}
}
Document
The Evolution of Interpretive Contexts in Stories
Abstract
Modeling the effect of context on interpretation, for the purposes of building intelligent systems, has been a long-standing problem: qualities of logic can restrict accurate contextual interpretation,
even when there is only one context to consider. Stories offer a range of structures that could extend formal theories of context, indicating how arrays of inferred contexts are able to knit together, making an ontological reference that is specific to the particular set of circumstances embodied in the tale. This derived ontology shifts as the text unfolds, enabling constant revision and the emergence of unexpected meanings. The described approach employs dynamic knowledge representation techniques to model how these structures are built and changed. Two new operators have been designed for this purpose: governance and causal conceptual agents. As an example, a few lines from the story Red Riding Hood As a Dictator Would Tell It are used to demonstrate how a story interpretive framework can be continually re-made, in a way that
produces unexpected interpretations of terms.
Cite as
Beth Cardier. The Evolution of Interpretive Contexts in Stories. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 23-38, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{cardier:OASIcs.CMN.2015.23,
author = {Cardier, Beth},
title = {{The Evolution of Interpretive Contexts in Stories}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {23--38},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.23},
URN = {urn:nbn:de:0030-drops-52784},
doi = {10.4230/OASIcs.CMN.2015.23},
annote = {Keywords: Story dynamism, contextual interpretation, ontological interoperability, retroactive revision, narrative progression in discourse processes, derived o}
}
Document
Structured Narratives as a Framework for Journalism: A Work in Progress
Abstract
This paper describes Structured Stories, a platform for producing and consuming journalism as structured narratives based on instantiations of event frames. The event frames are defined using FrameNet and are instantiated as structured events using references to nodes in various knowledge graphs. Structured narratives with recursive, fractal and network characteristics are then assembled from these structured events. The approach requires the direct reporting of journalistic events into structure by untrained reporters, and utilizes a simplified sequential user interface to achieve this. A prototype has been built and published, and is being applied to the reporting of local government journalism to explore editorial aspects of the approach.
Cite as
David A. Caswell. Structured Narratives as a Framework for Journalism: A Work in Progress. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 39-44, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{caswell:OASIcs.CMN.2015.39,
author = {Caswell, David A.},
title = {{Structured Narratives as a Framework for Journalism: A Work in Progress}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {39--44},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.39},
URN = {urn:nbn:de:0030-drops-52794},
doi = {10.4230/OASIcs.CMN.2015.39},
annote = {Keywords: journalism, frames, narrative structure, event representation}
}
Document
Impulse: a Formal Characterization of Story
Abstract
We present a novel representation of narratives at the story level called Impulse. It combines a temporal representation of a story’s actions and events with a representation of the mental models of the story’s characters into a cohesive, logic-based language. We show the expressiveness of this approach by encoding a story fragment, and compare it to other formal story representations in terms of representational dimensions. We also acknowledge the computational complexity of our approach and argue that a restricted subset still provides a high degree of expressive power
Cite as
Markus Eger, Camille Barot, and R. Michael Young. Impulse: a Formal Characterization of Story. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 45-53, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{eger_et_al:OASIcs.CMN.2015.45,
author = {Eger, Markus and Barot, Camille and Young, R. Michael},
title = {{Impulse: a Formal Characterization of Story}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {45--53},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.45},
URN = {urn:nbn:de:0030-drops-52800},
doi = {10.4230/OASIcs.CMN.2015.45},
annote = {Keywords: Narrative, logic, representation, mental models, time}
}
Document
Schemas for Narrative Generation Mined from Existing Descriptions of Plot
Abstract
Computational generation of literary artifacts very often resorts to template-like schemas that can be instantiated into complex structures. With this view in mind, the present paper reviews a number of existing attempts to provide an elementary set of patterns for basic plots. An attempt is made to formulate these descriptions of possible plots in terms of character functions, an abstraction of plot-bearing elements of a story originally formulated by Vladimir Propp. These character functions act as the building blocks of the Propper system, an existing framework for computational story generation. The paper explores the set of extensions required to the original set of character functions to allow for a basic representation of the analysed schemata, and a solution for automatic generation of stories based on this formulation of the narrative schemas. This solution uncovers important insights on the relative expressive power of the representation of narrative in terms of character functions, and their impact on the generative potential of the framework is discussed.
Cite as
Pablo Gervás, Carlos León, and Gonzalo Méndez. Schemas for Narrative Generation Mined from Existing Descriptions of Plot. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 54-71, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{gervas_et_al:OASIcs.CMN.2015.54,
author = {Gerv\'{a}s, Pablo and Le\'{o}n, Carlos and M\'{e}ndez, Gonzalo},
title = {{Schemas for Narrative Generation Mined from Existing Descriptions of Plot}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {54--71},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.54},
URN = {urn:nbn:de:0030-drops-52812},
doi = {10.4230/OASIcs.CMN.2015.54},
annote = {Keywords: Narrative generation, conceptual representation of narrative, character functions, plot, narrative schemas}
}
Document
Imaginative Recall with Story Intention Graphs
Abstract
Intelligent storytelling systems either formalize specific narrative structures proposed by narratologists (such as Propp and Bremond), or are founded on formal representations from artificial intelligence (such as plan structures from classical planning). This disparity in underlying knowledge representations leads to a lack of common evaluation metrics across story generation systems, particularly around the creativity aspect of generators. This paper takes Skald, a reconstruction of the Minstrel creative story generation system, and maps the representation to a formal narrative representation of Story Intention Graphs (SIG) proposed by Elson et al. This mapping facilitates the opportunity to expand the creative space of stories generated through imaginative recall in Minstrel while maintaining narrative complexity. We show that there is promise in using the SIG as an intermediate representation that is useful for evaluation of story generation systems.
Cite as
Sarah Harmon and Arnav Jhala. Imaginative Recall with Story Intention Graphs. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 72-81, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{harmon_et_al:OASIcs.CMN.2015.72,
author = {Harmon, Sarah and Jhala, Arnav},
title = {{Imaginative Recall with Story Intention Graphs}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {72--81},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.72},
URN = {urn:nbn:de:0030-drops-52829},
doi = {10.4230/OASIcs.CMN.2015.72},
annote = {Keywords: Story generation; computational creativity; narrative; story intention graph}
}
Document
Animacy Detection in Stories
Abstract
This paper presents a linguistically uninformed computational model for animacy classification. The model makes use of word n-grams in combination with lower dimensional word embedding representations that are learned from a web-scale corpus. We compare the model to a number of linguistically informed models that use features such as dependency tags and show competitive results. We apply our animacy classifier to a large collection of Dutch folktales to obtain a list of all characters in the stories. We then draw a semantic map of all automatically extracted characters which provides a unique entrance point to the collection.
Cite as
Folgert Karsdorp, Marten van der Meulen, Theo Meder, and Antal van den Bosch. Animacy Detection in Stories. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 82-97, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{karsdorp_et_al:OASIcs.CMN.2015.82,
author = {Karsdorp, Folgert and van der Meulen, Marten and Meder, Theo and van den Bosch, Antal},
title = {{Animacy Detection in Stories}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {82--97},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.82},
URN = {urn:nbn:de:0030-drops-52841},
doi = {10.4230/OASIcs.CMN.2015.82},
annote = {Keywords: animacy detection, word embeddings, folktales}
}
Document
The Love Equation: Computational Modeling of Romantic Relationships in French Classical Drama
Abstract
We report on building a computational model of romantic relationships in a corpus of historical literary texts. We frame this task as a ranking problem in which, for a given character, we try to assign the highest rank to the character with whom (s)he is most likely to be romantically involved. As data we use a publicly available corpus of French 17th and 18th century plays (http://www.theatre-classique.fr/) which is well suited for this type of analysis because of the rich markup it provides (e.g. indications of characters speaking). We focus on distributional, so-called second-order features, which capture how speakers are contextually embedded in the texts. At a mean reciprocal rate (MRR) of 0.9 and MRR@1 of 0.81, our results are encouraging, suggesting that this approach might be successfully extended to other forms of social interactions in literature, such as antagonism or social power relations.
Cite as
Folgert Karsdorp, Mike Kestemont, Christof Schöch, and Antal van den Bosch. The Love Equation: Computational Modeling of Romantic Relationships in French Classical Drama. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 98-107, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{karsdorp_et_al:OASIcs.CMN.2015.98,
author = {Karsdorp, Folgert and Kestemont, Mike and Sch\"{o}ch, Christof and van den Bosch, Antal},
title = {{The Love Equation: Computational Modeling of Romantic Relationships in French Classical Drama}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {98--107},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.98},
URN = {urn:nbn:de:0030-drops-52838},
doi = {10.4230/OASIcs.CMN.2015.98},
annote = {Keywords: French drama, social relations, neural network, representation learning}
}
Document
Learning Components of Computational Models from Texts
Abstract
The mental models of experts can be encoded in computational cognitive models that can support the functioning of intelligent agents. This paper compares human mental models to computational cognitive models, and explores the extent to which the latter can be acquired automatically from published sources via automatic learning by reading. It suggests that although model components can be automatically learned, published sources lack sufficient information for the compilation of fully specified models that can support sophisticated agent capabilities, such as physiological simulation and reasoning. Such models require hypotheses and educated guessing about unattested phenomena, which can be provided only by humans and are best recorded using knowledge engineering strategies. This work merges past work on cognitive modeling, agent simulation, learning by reading, and narrative structure, and draws examples from the domain of clinical medicine.
Cite as
Marjorie McShane, Sergei Nirenburg, Bruce Jarrell, and George Fantry. Learning Components of Computational Models from Texts. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 108-123, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{mcshane_et_al:OASIcs.CMN.2015.108,
author = {McShane, Marjorie and Nirenburg, Sergei and Jarrell, Bruce and Fantry, George},
title = {{Learning Components of Computational Models from Texts}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {108--123},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.108},
URN = {urn:nbn:de:0030-drops-52856},
doi = {10.4230/OASIcs.CMN.2015.108},
annote = {Keywords: cognitive modeling, simulation, clinical medicine, learning by reading}
}
Document
Cross-Document Narrative Frame Alignment
Abstract
Automated cross-document comparison of narrative facilitates co-reference and event similarity identification in the retellings of stories from different perspectives. With attention to these outcomes, we introduce a method for the unsupervised generation and comparison of graph representations of narrative texts. Composed of the entity-entity relations that appear in the events of a narrative, these graphs are represented by adjacency matrices populated with text extracted using various natural language processing tools. Graph similarity analysis techniques are then used to measure the similarity of events and the similarity of character function between stories. Designed as an automated process, our first application of this method is against a test corpus of 10 variations of the Aarne-Thompson type 333 story, "Little Red Riding Hood." Preliminary experiments correctly co-referenced differently named entities from story variations and indicated the relative similarity of events in different iterations of the tale despite their order differences. Though promising, this work in progress also indicated some incorrect correlations between dissimilar entities.
Cite as
Ben Miller, Ayush Shrestha, Jennifer Olive, and Shakthidhar Gopavaram. Cross-Document Narrative Frame Alignment. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 124-132, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{miller_et_al:OASIcs.CMN.2015.124,
author = {Miller, Ben and Shrestha, Ayush and Olive, Jennifer and Gopavaram, Shakthidhar},
title = {{Cross-Document Narrative Frame Alignment}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {124--132},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.124},
URN = {urn:nbn:de:0030-drops-52867},
doi = {10.4230/OASIcs.CMN.2015.124},
annote = {Keywords: computational narrative, natural language processing, graph theory, text mining}
}
Document
Towards Narrative-Based Knowledge Representation in Cognitive Systems
Abstract
The hypothesis according to which narrative is not only a prominent form of human com- munication but also a fundamental way to represent knowledge and to structure the mind has been limitedly but increasingly discussed for the last 40 years. However, in the realm of Artificial Intelligence, it did not lead to an elaborate model of knowledge representation, beyond scripts and cases. In this paper, we attempt to go further by identifying three differentiating features of narratives that may inspire novel forms of knowledge representation: transformation, conflict and unactualized events. In particular, these three features open the way for knowledge representation formalisms that take greater account of the co-existence of intertwined conflicting representations, with various validities and validity domains, beyond a purely factual representation of the world.
Cite as
Nicolas Szilas. Towards Narrative-Based Knowledge Representation in Cognitive Systems. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 133-141, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{szilas:OASIcs.CMN.2015.133,
author = {Szilas, Nicolas},
title = {{Towards Narrative-Based Knowledge Representation in Cognitive Systems}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {133--141},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.133},
URN = {urn:nbn:de:0030-drops-52871},
doi = {10.4230/OASIcs.CMN.2015.133},
annote = {Keywords: cognitive science, narrative theories, knowledge representation}
}
Document
Governing Narrative Events With Institutional Norms
Abstract
A narrative world can be viewed as a form of society in which characters follow a set of social norms whose collective function is to guide the characters through (the creation of) a story arc and reach some conclusion. By modelling the rules of a narrative using norms, we can govern the actions of agents that act out the characters in a story. Agents are given sets of permitted actions and obligations to fulfil based on their and the story’s current situation. However, the decision to conform to these expectations is ultimately left to the agent. This means that the characters have control over fine-grained elements of the story, resulting in a more flexible and dynamic narrative experience. This would allow the creator of an interactive narrative to specify only the general structure of a story, leaving the details to the agents. We illustrate a particular realisation of this vision using a formalization of Propp’s morphology in a normative social framework, with belief-desire-intention agents playing the characters.
Cite as
Matt Thompson, Julian Padget, and Steve Battle. Governing Narrative Events With Institutional Norms. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 142-151, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{thompson_et_al:OASIcs.CMN.2015.142,
author = {Thompson, Matt and Padget, Julian and Battle, Steve},
title = {{Governing Narrative Events With Institutional Norms}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {142--151},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.142},
URN = {urn:nbn:de:0030-drops-52889},
doi = {10.4230/OASIcs.CMN.2015.142},
annote = {Keywords: institutions, norms, narrative, agents}
}
Document
Good Timing for Computational Models of Narrative Discourse
Abstract
The temporal order in which story events are presented in discourse can greatly impact how readers experience narrative; however, it remains unclear how narrative systems can leverage temporal order to affect comprehension and experience. We define structural properties of discourse which provide a basis for computational narratologists to reason about good timing, such as when readers learn about event relationships.
Cite as
David R. Winer, Adam A. Amos-Binks, Camille Barot, and R. Michael Young. Good Timing for Computational Models of Narrative Discourse. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 152-156, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{winer_et_al:OASIcs.CMN.2015.152,
author = {Winer, David R. and Amos-Binks, Adam A. and Barot, Camille and Young, R. Michael},
title = {{Good Timing for Computational Models of Narrative Discourse}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {152--156},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.152},
URN = {urn:nbn:de:0030-drops-52897},
doi = {10.4230/OASIcs.CMN.2015.152},
annote = {Keywords: causal inference, narrative, discourse structure, computational model}
}
Document
Model-based Story Summary
Abstract
A story summarizer benefits greatly from a reader model because a reader model enables the story summarizer to focus on delivering useful knowledge in minimal time with minimal effort. Such a summarizer can, in particular, eliminate disconnected story elements, deliver only story elements connected to conceptual content, focus on particular concepts of interest, such as revenge, and make use of our human tendency to see causal connection in adjacent sentences. Experiments with a summarizer, built on the Genesis story understanding system, demonstrate considerable compression of an 85-element précis of the plot of Shakespeare’s Macbeth, reducing it, for example, to the 14 elements that make it a concise summary about Pyrrhic victory. Refocusing the summarizer on regicide reduces the element count to 7, or 8% of the original.
Cite as
Patrick Henry Winston. Model-based Story Summary. In 6th Workshop on Computational Models of Narrative (CMN 2015). Open Access Series in Informatics (OASIcs), Volume 45, pp. 157-165, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)
Copy BibTex To Clipboard
@InProceedings{winston:OASIcs.CMN.2015.157,
author = {Winston, Patrick Henry},
title = {{Model-based Story Summary}},
booktitle = {6th Workshop on Computational Models of Narrative (CMN 2015)},
pages = {157--165},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-939897-93-4},
ISSN = {2190-6807},
year = {2015},
volume = {45},
editor = {Finlayson, Mark A. and Miller, Ben and Lieto, Antonio and Ronfard, Remi},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.CMN.2015.157},
URN = {urn:nbn:de:0030-drops-52900},
doi = {10.4230/OASIcs.CMN.2015.157},
annote = {Keywords: story telling and summarization, story understanding, cognitive modeling}
}