Pathways to the Native Storyteller: A Method to Enable Computational Storytelling (original) (raw)

Cognitive and Computer Systems for Understanding Narrative Text

This project continues our interdisciplinary research into computational and cognitive aspects of narrative comprehension. Our ultimate goal is the development of a computational theory of how humans understand narrative texts. The theory will be informed by joint research from the viewpoints of linguistics, cognitive psychology, the study of language acquisition, literary theory, geography, philosophy, and artificial intelligence. The linguists, literary theorists, and geographers in our group are developing theories of narrative language and spatial understanding that are being tested by the cognitive psychologists and language researchers in our group, and a computational model of a reader of narrative text is being developed by the AI researchers, based in part on these theories and results and in part on research on knowledge representation and reasoning. This proposal describes the knowledge-representation and natural-language-processing issues involved in the computational implementation of the theory; discusses a contrast between communicative and narrative uses of language and of the relation of the narrative text to the story world it describes; investigates linguistic, literary, and hermeneutic dimensions of our research; presents a computational investigation of subjective sentences and reference in narrative; studies children's acquisition of the ability to take third-person perspective in their own storytelling; describes the psychological validation of various linguistic devices; and examines how readers develop an understanding of the geographical space of a story. This report is a longer version of a project description submitted to NSF. This document, produced in 1 This project continues our interdisciplinary research into computational and cognitive aspects of narrative comprehension . Our ultimate goal is the development of a computational theory of how humans understand narrative texts. The theory will be informed by joint research from the viewpoints of linguistics, cognitive psychology, the study of language acquisition, literary theory, geography, philosophy, and artificial intelligence. The linguists, literary theorists, and geographers in our group are developing theories of narrative language and spatial understanding that are being tested by the cognitive psychologists and language researchers in our group, and a computational model of a reader of narrative text is being developed by the AI researchers, based in part on these theories and results and in part on research on knowledge representation and reasoning.

Steps Towards a System to Extract Formal Narratives from Text

2019

In this paper we present a first step towards a system to extract formal narratives from text. This work is part of a wider research on the introduction of narratives in Digital Libraries. We represent narratives as networks of events, each set in space and time, endowed with factual components, and linked to each other through semantic relations. In order to extract a narrative from text, the first step is to automatically detect and classify the events in the text. We present a software we developed that uses neural networks for event detection and classification. It was trained on a dataset of annotated biographies of writers and artists from the English Wikipedia and on the ACE 2005 training corpus. We tested the software on the biography of Florentine poet Dante Alighieri. This software constitutes the first component of a broader system for narrative extraction from natural language text.

An exploration of automated narrative analysis via machine learning

PLOS ONE

The accuracy of four machine learning methods in predicting narrative macrostructure scores was compared to scores obtained by human raters utilizing a criterion-referenced progress monitoring rubric. The machine learning methods that were explored covered methods that utilized hand-engineered features, as well as those that learn directly from the raw text. The predictive models were trained on a corpus of 414 narratives from a normative sample of school-aged children (5;0-9;11) who were given a standardized measure of narrative proficiency. Performance was measured using Quadratic Weighted Kappa, a metric of inter-rater reliability. The results indicated that one model, BERT, not only achieved significantly higher scoring accuracy than the other methods, but was consistent with scores obtained by human raters using a valid and reliable rubric. The findings from this study suggest that a machine learning method, specifically, BERT, shows promise as a way to automate the scoring of narrative macrostructure for potential use in clinical practice.

NKRL, a knowledge representation tool for encoding the ‘meaning’ of complex narrative texts

Natural Language Engineering, 1997

In this paper, we describe NKRL (Narrative Knowledge Representation Language), a language designed for representing, in a standardized way, the semantic content (the ‘meaning’) of complex narrative texts. After having introduced informally the four ‘components’ (specialized sub-languages) of NKRL, we will describe (some of) the data structures proper to each of them, trying to show that the NKRL coding retains the main informational elements of the original narrative expressions. We will then focus on an important subset of NKRL, the so-called AECS sub-language, showing in particular that the operators of this sub-language can be used to represent some sorts of ‘plural’ expressions.

The automatic generation of narratives

2007

We present the Narrator, a Natural Language Generation component used in a digital storytelling system. The system takes as input a formal representation of a story plot, in the form of a causal network relating the actions of the characters to their motives and their consequences. Based on this input, the Narrator generates a narrative in Dutch, by carrying out tasks such as constructing a Document Plan, performing aggregation and ellipsis and the generation of appropriate referring expressions. We describe how these tasks are performed and illustrate the process with examples, showing how this results in the generation of coherent and well-formed narrative texts.

LISA: Lexically Intelligent Story Assistant

This paper serves as an introduction to building an assistive tool for story writers. Our tool, Lexically Intelligent Story Assistant (or LISA), aims to assist story writers by providing real-time feedback on lexical inconsistencies in the story. LISA analyzes the narrative and builds a knowledge base, using artificial intelligence to make inferences and point out errors in the narrative. Moreover, it also allows the user to interact with the system by querying the knowledge base in natural language form. This tool shows that it is possible to create a database for a narrative and use artificial intelligence to improve authoring of stories.

A survey on narrative extraction from textual data

Artificial Intelligence Review

Narratives are present in many forms of human expression and can be understood as a fundamental way of communication between people. Computational understanding of the underlying story of a narrative, however, may be a rather complex task for both linguists and computational linguistics. Such task can be approached using natural language processing techniques to automatically extract narratives from texts. In this paper, we present an in depth survey of narrative extraction from text, providing a establishing a basis/framework for the study roadmap to the study of this area as a whole as a means to consolidate a view on this line of research. We aim to fulfill the current gap by identifying important research efforts at the crossroad between linguists and computer scientists. In particular, we highlight the importance and complexity of the annotation process, as a crucial step for the training stage. Next, we detail methods and approaches regarding the identification and extraction ...

A Semantically-Based Computational Approach to Narrative Structure

2017

In this paper we will define narrative structure as characterized by a basic element, the narreme, which is here described as the basic unit of narrative structure, the smallest possible unit of the story. We annotated a full novel – "The Solid Mandala" (1966) by Nobel laureate Patrick White – combining two approaches: one is related to sentiment and opinion mining, including deeper aspects connected to event factuality and subjectivity, and the other focuses on evaluative features derived from the Appraisal Theory framework. After characterizing the style, we will show the main significant events of the plot as they emerge from the distribution of deep semantic features. Narreme boundaries will be identified by presence of specific speech acts, change of point of view, and movement in spatio-temporal coordinates through flashbacks. An experiment with our system of text understanding, GETARUNS, has been carried out to test its ability to automatically identify narremes.

Automatic Detection of Narrative Structure for High-Level Story Representation

2018

Automatic summarization is dominated by approaches which focus on the selection and concatenation of material in a text. What can be achieved by such approaches is intrinsically limited and far below what can be achieved by human summarizers. There is evidence that successfully creating a rich representation of text, including details of its narrative structure, would help to create more human-like summaries. This paper describes a part of our ongoing work on a cognitively inspired, creative approach to summarization. Here we detail our work on the detection of narrative structure in order to help build rich interpretations of a text and help give rise to a creative approach to summarization. In particular we consider the domain of Russian folktales. Using Vladimir Propp's thorough description of the interrelations between the narrative elements of such tales, we pose this task as a constraint satisfaction problem. While we only consider this small domain, our approach can be applied to any domain of text on which enough constraints can be placed.