Deriving Salience Models from Human Route Directions
2013 (English)In: Workshop on Computational Models of Spatial Language Interpretation and Generation 2013: (CoSLI-3), 2013Conference paper (Refereed)
We present an approach to derive individual preferences in the use of landmarks for route instructions in a city environment. Each possible landmark that a person can refer to in a given situation is modelled as a feature vector, and the preference (or salience) associated with the landmark can be computed as a weighted sum of these features. The weight vector, representing the person's personal salience model, is automatically derived from the person's own route descriptions. Experiments show that the derived salience models can correctly predict the user's choice of landmark in 69% of the cases.
Place, publisher, year, edition, pages
Language Technology (Computational Linguistics)
IdentifiersURN: urn:nbn:se:kth:diva-136933ISBN: 978-1-62748-401-5OAI: oai:DiVA.org:kth-136933DiVA: diva2:677478
CoSLI-3: Workshop on Computational Models of Spatial Language Interpretation and Generation, Co-located with the 10th International Conference on Computational Semantics; Potsdam, Germany, March 19, 2013
QC 201401242013-12-092013-12-092014-01-24Bibliographically approved