Academia.eduAcademia.edu

Outline

Title
Abstract
General Introduction
Related Work
Conclusions and Future Work
References
All Topics
Psychology
Cognitive Psychology

Narrative text comprehension: From Psychology to AI

Profile image of Rob MillerRob MillerProfile image of Irene-Anna DiakidoyIrene-Anna Diakidoy

Abstract

This paper brings together the theory of Argumentation in AI with the Psychology of Story Comprehension to develop a KRR framework for Narrative Text Comprehension. The proposed framework is based on a computational understanding of the general psychological principles of coherency and cognitive economy for text comprehension. In this first part of the study the work concentrates on the central problem of integration (or elaboration) of the explicit information from the text with the implicit (in the reader's mind) common sense world knowledge pertaining to the topic(s) of the story given in the text. We show how the major challenges for a successful story comprehension are closely related to those of NMR, as found in Default Reasoning and Reasoning about Action and Change and the specific problems of Knowledge Qualification and Revision within these areas and, how an appropriate formulation through argumentation can give a basis for automating the construction and revision of a coherent comprehension model of a narrative. We report on a first set of empirical experiments to harness the implicit world knowledge used by humans reading a story to guide the background knowledge given as input to our framework and present a prototype system that is used to evaluate the ability of our approach to capture both the majority and the variability of understanding of a story by the human readers in the experiment. The strong inter-disciplinary nature of our work can help us to examine closely and improve our understanding of the computational nature of common sense knowledge while at the same time offering a concrete and important testbed for evaluating the development of KRR frameworks in AI.

Related papers

Knowledge Activation in Story Comprehension
Antonis Kakas

Journal of Cognitive Science

The purpose of this study was to provide behavioral data regarding the world knowledge that readers activate during story comprehension with a view to inform the development of formal and computational representation of knowledge for automated comprehension. The focus of the study was on the amount, the structural aspects, and the coherence function of the activated knowledge. In a knowledge elicitation task, undergraduate students recorded the knowledge they deemed necessary for understanding each sentence in a set of four short stories in the form of property and causal knowledge rules. Results indicated the activation of a limited amount of knowledge that maintained both situational and conceptual connections with input. Situational inferencing and continuity (i.e., carrying over of previously activated ideas) were positively associated and varied as a function of story part. Findings are discussed in relation to dominant theoretical models of narrative comprehension and for their implications regarding the computational representation of knowledge in automated story comprehension.

View PDFchevron_right
Cognitive and Computer Systems for Understanding Narrative Text
William Rapaport

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.

View PDFchevron_right
A Computational Model of On-Line Story Understanding
Elliot Smith

Citeseer, 1997

Models of story understanding in artificial intelligence and cognitive psychology typically concentrate on the construction of representations of story content. Construction of a 'complete' representation (informally equivalent to an 'understanding') requires inferences which establish coherence links between text statements. This report examines how reality-based links (e.g. causal connections) and narrative-based links (e.g. those that establish rhetorical structure and delineate text segments) have been handled in previous models. My suggestion is that both types of links are required for narrative understanding, and that each is dependent on the other. I also indicate how the inferences required to create both types of link may be uniformly represented and processed within a story grammar framework. This framework could also be used to model theories about recall (hierarchical storage) and processing.

View PDFchevron_right

References (36)

  1. Albrecht, J. E., and O'Brien, E. J. 1993. Updating a mental model: Maintaining both local and global coherence. Jour- nal of Experimental Psychology: Learning, Memory, and Cognition 19:1061-1070.
  2. Baker, C. F.; Fillmore, C. J.; and Lowe, J. B. 1998. The Berkeley FrameNet Project. In Proceedings of the 36th An- nual Meeting of the Association for Computational Linguis- tics and 17th International Conference on Computational Linguistics -Volume 1, ACL '98, 86-90.
  3. Brewer, W., and Lichtenstein, E. 1982. Stories are to enter- tain: A structural-affect theory of stories. Journal of Prag- matics 6:473-486.
  4. Crain-Thoreson, C.; Lippman, M. Z.; and McClendon- Magnuson, D. 1997. Windows on comprehension: read- ing comprehension processes as revealed by two think-aloud procedures. Journal of Educational Psychology 89:579- 591. Dahlgren, K.; McDowell, J.; and Stabler, E. 1989. Knowledge representation for commonsense reasoning with text. Computational Linguistics 15(3):149-170. http://acl.ldc.upenn.edu/J/J89/J89-3002.pdf.
  5. Gernsbacher, M. A. 1990. Language comprehension as structure building. Hillsdale, NJ: Erlbaum.
  6. Gerrig, R. J., and O'Brien, E. J. 2005. The scope of memory- based processing. Discourse Processes.
  7. Graesser, A. C.; Millis, K. K.; and Zwaan, R. A. 1997. Dis- course comprehension. Annual Review of Psychology 48.
  8. Kakas, A. C.; Mancarella, P.; Sadri, F.; Stathis, K.; and Toni, F. 2008. Computational Logic Foundations of KGP Agents. J. Artif. Intell. Res. (JAIR) 33:285-348.
  9. Kintsch, W. 1988. The role of knowledge in discourse com- prehension: A construction-integration model. Psychologi- cal Review 95:163-182.
  10. Kintsch, W. 2005. An overview of top-down and bottom-up effects in comprehension: The C-I perspective. Discourse Processes.
  11. Kowalski, R., and Sergot, M. 1986. A Logic-Based Calculus of Events. New Generation Computing 4(1):67-95.
  12. Lenat, D. B. 1995. CYC: A Large-Scale Investment in Knowledge Infrastructure. Communications of the ACM 38(11):32-38.
  13. Levesque, H. J.; Davis, E.; and Morgenstern, L. 2011. The Winograd Schema Challenge. In Proceedings of the Thir- teenth International Conference on Principles of Knowledge Representation and Reasoning.
  14. Mandler, J. M., and Johnson, N. S. 1977. Remembrance of things parsed: Story structure and recall. Cognitive Psychol- ogy 9:11-151.
  15. Mani, I. 2013. Computational Modeling of Narrative. Mor- gan and Claypool.
  16. McNamara, D. S., and Magliano, J. 2009. Toward a compre- hensive model of comprehension. The Psychology of Learn- ing and Motivation 51:297-384.
  17. Michael, L., and Valiant, L. G. 2008. A First Experimental Demonstration of Massive Knowledge Infusion. In Proc. of 11th International Conference on Principles of Knowledge Representation and Reasoning (KR'08), 378-389.
  18. Michael, L. 2009. Reading Between the Lines. In Proc. of 21st International Joint Conference on Artificial Intelligence (IJCAI'09), 1525-1530.
  19. Michael, L. 2013a. Machines with Websense. In Proc. of 11th International Symposium on Logical Formalizations of Commonsense Reasoning (Commonsense'13).
  20. Michael, L. 2013b. Story Understanding... Calculemus! In Proc. of 11th International Symposium on Logical Formal- izations of Commonsense Reasoning (Commonsense'13).
  21. Miller, G. A. 1995. WordNet: A Lexical Database for En- glish. Communications of the ACM 38(11):39-41.
  22. Modgil, S., and Prakken, H. 2012. A general account of argumentation with preferences. Artificial Intelligence 195:361-397.
  23. Mueller, E. 2002. Story understanding. In Nadel, L., ed., En- cyclopedia of Cognitive Science, volume 4, 238-246. Lon- don: Nature Publishing Group.
  24. Mueller, E. 2003. Story understanding through multi- representation model construction. In Hirst, G., and Niren- burg, S., eds., Text Meaning: Proceedings of the HLT- NAACL 2003 Workshop, 46-53. East Stroudsburg, PA: As- sociation for Computational Linguistics.
  25. Mueller, E. 2004. Understanding script-based stories us- ing commonsense reasoning. Cognitive Systems Research 5(4):307-340.
  26. Mueller, E. 2013. Story understanding resources. http://xenia.media.mit.edu/ mueller/storyund/storyres.html. Accessed February 28, 2013.
  27. Palmer, M.; Gildea, D.; and Kingsbury, P. 2005. The Propo- sition Bank: An Annotated Corpus of Semantic Roles. Com- putational Linguistics 31(1):71-106.
  28. Rao, A. S., and Georgeff, M. P. 1995. BDI Agents: From Theory to Practice. In First International Conference On Multi-Agent Systems (ICMAS-95), 312-319.
  29. Rapp, D. N., and Taylor, H. A. 2004. Interactive dimensions in the construction of mental representations for text. Jour- nal of Experimental Psychology: Learning, Memory, and Cognition 30:988-1001.
  30. Rumelhart. 1975. Notes on a schema for stories. In Bobrow, D. G., and Collins, A., eds., Representation and understand- ing: Studies in cognitive science, 211-236. New York: Aca- demic Press.
  31. van den Broek, P.; Lorch, R. F.; Linderholm, T.; and Gustafson, M. 2001. The effects of readers' goals on in- ference generation and memory for texts. Memory and Cog- nition 29:1081-1087.
  32. van den Broek, P. 1994. Comprehension and memory of narrative texts: Inferences and coherence. In Gernsbacher, M. A., ed., Handbook of psycholinguistics, 539-588. Lon- don, UK: Academic Press.
  33. van Harmelen, F.; Lifschitz, V.; and Porter, B. 2008. Hand- book of Knowledge Representation. Elsevier Science. ISBN: 978-0-444-52211-5.
  34. van Lambalgen, M., and Hamm, F. 2005. The Proper Treat- ment of Events. Blackwell.
  35. Zwaan, R. A., and Radvansky, G. A. 1998. Situation mod- els in language comprehension and memory. Psychological Bulletin 123:162-185.
  36. Zwaan, R. A.; Langston, M. C.; and Graesser, A. C. 1995. The construction of situation models in narrative compre- hension: An event-indexing model. Psychological Science 6:292-297.

Related papers

Story comprehension through argumentation
Irene-Anna Diakidoy, Rob Miller

This paper presents a novel application of argumentation for automated Story Comprehension (SC). It uses argumentation to develop a computational approach for SC as this is understood and studied in psychology. Argumentation provides uniform solutions to various representational and reasoning problems required for SC such as the frame, ramification, and qualification problems, as well as the problem of contrapositive reasoning with default information. The grounded semantics of argumentation provides a suitable basis for the construction and revision of comprehension models, through the synthesis of the explicit information from the narrative in the text with the implicit (in the reader's mind) common sense world knowledge pertaining to the topic(s) of the story given in the text. We report on the empirical evaluation of the approach through a prototype system and its ability to capture both the majority and the variability of understanding of stories by human readers. This application of argumentation can provide an important test-bed for the more general development of computational argumentation.

View PDFchevron_right
A Psychology-Inspired Approach to Automated Narrative Text Comprehension
Irene-Anna Diakidoy

2014

We report on an ongoing research program to develop a formal framework for automated narrative text comprehension, bringing together know-how from research in Artificial Intelligence and the Psychology of Reading and Comprehension. It uses argumentation to capture appropriate solutions to the frame, ramification, and qualification problems, and their generalizations as required for text comprehension. In this first part of the study we concentrate on the central problem of integration of the explicit information from the text narrative with the reader's implicit commonsense world knowledge, and the associated tasks of elaboration and revision.

View PDFchevron_right
Non-monotonic reasoning and story comprehension
Rob Miller, Irene-Anna Diakidoy

This paper develops a Reasoning about Actions and Change framework integrated with Default Reasoning, suitable as a Knowledge Representation and Reasoning framework for Story Comprehension. The proposed framework, which is guided strongly by existing knowhow from the Psychology of Reading and Comprehension, is based on the theory of argumentation from AI. It uses argumentation to capture appropriate solutions to the frame, ramification and qualification problems and generalizations of these problems required for text comprehension. In this first part of the study the work concentrates on the central problem of integration (or elaboration) of the explicit information from the narrative in the text with the implicit (in the reader's mind) common sense world knowledge pertaining to the topic(s) of the story given in the text. We also report on our empirical efforts to gather background common sense world knowledge used by humans when reading a story and to evaluate, through a prototype system, the ability of our approach to capture both the majority and the variability of understanding of a story by the human readers in the experiments.

View PDFchevron_right
4 Non-Monotonic Reasoning and Story Comprehension
Irene-Anna Diakidoy

2016

This paper develops a Reasoning about Actions and Change framework integrated with Default Reasoning, suitable as a Knowledge Representation and Reasoning framework for Story Comprehension. The proposed framework, which is guided strongly by existing knowhow from the Psychology of Reading and Comprehension, is based on the theory of argumentation from AI. It uses argumentation to capture appropriate solutions to the frame, ramification and qualification problems and generalizations of these problems required for text comprehension. In this first part of the study the work concentrates on the central problem of integration (or elaboration) of the explicit information from the narrative in the text with the implicit (in the reader's mind) common sense world knowledge pertaining to the topic(s) of the story given in the text. We also report on our empirical efforts to gather background common sense world knowledge used by humans when reading a story and to evaluate, through a prototype system, the ability of our approach to capture both the majority and the variability of understanding of a story by the human readers in the experiments.

View PDFchevron_right
STAR: A System of Argumentation for Story Comprehension and Beyond
Rob Miller

National Conference on Artificial Intelligence, 2015

This paper presents the STAR system, a system for automated narrative comprehension, developed on top of an argumentation-theoretic formulation of defeasible reasoning, and strongly following guidelines from the psychology of comprehension. We discuss the system's use in psychological experiments on story comprehension, and our plans for its broader use in empirical studies concerning wider issues of commonsense reasoning.

View PDFchevron_right

Related topics

  • Narrative Comprehension
  • Intelligent Computational Systems
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved