C4.5: programs for machine learning
C4.5: programs for machine learning
Assessing agreement on classification tasks: the kappa statistic
Computational Linguistics
Data mining: practical machine learning tools and techniques with Java implementations
Data mining: practical machine learning tools and techniques with Java implementations
Extending TimeML with typical durations of events
ARTE '06 Proceedings of the Workshop on Annotating and Reasoning about Time and Events
The exploitation of spatial information in narrative discourse
IWCS '11 Proceedings of the Ninth International Conference on Computational Semantics
Spatial role labeling: Towards extraction of spatial relations from natural language
ACM Transactions on Speech and Language Processing (TSLP)
| Hi-index | 0.00 |
Expanding on recent research into the predictability of explicit linguistic spatial information relative to features of discourse structure, we present the results of several machine learning studies which leverage rhetorical relations, events, temporal information, text sequence, and both explicit and implicit linguistic spatial information in three different corpora of narrative discourses. On average, classifiers predict figure, ground, spatial verb and preposition and frame of reference to 75% accuracy, rhetorical relations to 72% accuracy, and events to 76% accuracy (all values have statistical significance above majority class baselines). These results hold independent of the number of authors, subject matter, length and density of spatial and temporal information. Consequently, we argue for a generalized model of spatiotemporal information in narrative discourse, which not only provides a deeper understanding of the semantics and pragmatics of discourse structure, but also alternative robust approaches to analysis.