Segmenting narrative text into coherent scenes

Hideki Kozima, Teiji Furugori

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)


This paper describes a quantitative indicator for segmenting narrative text into coherent scenes. The indicator, called the lexical cohension profile (LCP), records lexical cohesiveness of words in a fixed-length window moving word by word on the text. The cohesiveness of words, which represents their coherence, is computed by spreading activation on a semantic network The basic idea of LCP is: (1) if the window is inside a scene, the words in it tend to be cohesive, and (2) if the window is crossing a scene boundary, the words in it tend to be incohesive. Comparison with the scene boundaries marked by a number of subjects shows that hills and valleys of the graph of LCP closely correlates with the human judgements. LCP may provide valuable information for text analysis, especially for resolving anaphora and ellipsis.

Original languageEnglish
Pages (from-to)13-19
Number of pages7
JournalLiterary and Linguistic Computing
Issue number1
Publication statusPublished - 1994
Externally publishedYes

ASJC Scopus subject areas

  • Information Systems
  • Language and Linguistics
  • Linguistics and Language


Dive into the research topics of 'Segmenting narrative text into coherent scenes'. Together they form a unique fingerprint.

Cite this