Conceptual Information Processing
Conceptual Information Processing
Toward plot units: automatic affect state analysis
CAAGET '10 Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text
Automatically producing plot unit representations for narrative text
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Hi-index | 0.01 |
Most research on narrative text summarisation has been conducted within the paradigm of experimental psychology. But recent language processing research in artificial intelligence suggests that the predominant theory of text summarisation requires further examination. Seemingly minor structural modifications of a story can result in significant alterations of summary behavior. In this paper, highlights of summary data from 72 subjects are presented and analyzed in terms of two competing summarization models: (1) the story grammar model of psychology, and (2) the plot unit model developed in artificial intelligence. We will show how selected story grammar predictions compare to plot unit predictions for short term summarization and then identify two complicating factors that have a major impact on summarisation behavior.