Corpus ID: 16374622

The Exploitation of Spatial Information in Narrative Discourse

@inproceedings{Howald2011TheEO,
  title={The Exploitation of Spatial Information in Narrative Discourse},
  author={B. Howald and E. G. Katz},
  booktitle={IWCS},
  year={2011}
}
  • B. Howald, E. G. Katz
  • Published in IWCS 2011
  • Computer Science
  • We present the results of several machine learning tasks that exploit explicit spatial language to classify rhetorical relations and the spatial information of narrative events. Three corpora are annotated with figure and ground (granularity) relationships, mereotopologically classified verbs and prepositions, and frames of reference. For rhetorical relations, Naive Bayesian models achieve 84.90% and 57.87% accuracy in classifying NARRATION and BACKGROUND/ELABORATION relations respectively (16… CONTINUE READING
    3 Citations

    Figures, Tables, and Topics from this paper

    The Use of Granularity in Rhetorical Relation Prediction
    • 4
    • PDF
    Spatial Role Labeling Annotation Scheme
    • 9
    • PDF

    References

    SHOWING 1-10 OF 33 REFERENCES
    Linguistic spatial classifications of event domains in narratives of crime
    • B. Howald
    • Computer Science
    • J. Spatial Inf. Sci.
    • 2010
    • 6
    The Rhetorical Parsing of Unrestricted Texts: A Surface-based Approach
    • D. Marcu
    • Computer Science
    • Computational Linguistics
    • 2000
    • 250
    • PDF
    Spatial reference in narrative domains
    • 43
    Spatial Language and Dialogue
    • 64
    • Highly Influential
    • PDF
    Improving summarization through rhetorical parsing tuning
    • 88
    Exploiting Linguistic Cues to Classify Rhetorical Relations
    • 55
    • Highly Influential
    • PDF
    On the coherence and structure of discourse
    • 518
    • PDF
    Rhetorical Structure Theory: A Framework for the Analysis of Texts
    • 304
    • PDF
    Inferring Sentence-internal Temporal Relations
    • 70
    • Highly Influential
    • PDF