DOWNLOAD THE GRE3D3 CORPUS

Many referring expression generation algorithms don't attempt to include spatial relations between the target referent and landmark objects into the descriptions they produce at all. Most systems that are able to deal with spatial relations only use them if the referent can't be uniquely identified without them. An interesting exception is the first one that appeared in the literature, Dale & Haddock's (1991) Relational Algorithm, which however showed extremely cumbersome descriptions in my first evaluation experiment of existing algorithms.

The prevalent hypothesis that spatial relations should only be used as a last resort (I call it the "absolute before relational" hypothesis) is usually justified by psycholinguistic findings suggesting that they cause a higher cognitive load for both speaker and listener. However, it seems quite obvious to me that in many situation the use of a spatial relation would be much both easier to produce and easier to undersand than a (possibly long) list of non-relational properties. For example, if I want a certain book that looks similar to a lot of the other books, mentioning the fact that it's just left of the big red one would be a better way to go than, for example, making the listener read the titles of all the little black books to find the one I mean.

To put the "absolute properties before relations" hypothesis to the test, I conducted a web-based production experiment and collected a corpus of 720 referring expressions for very simple objects in very simple 3D scenes, the GRE3D3 corpus. In all scenes it was possible to identify the target without using relations, however over a third of the descriptions nonetheless contained spatial relations. A few hypotheses about the factors influencing the use of spatial relations can be drawn from the data, however to establish their validity I am now planning more specific experiments.
The data gathering experiment and analysis of the corpus are detailed in

Jette Viethen and Robert Dale (2008). The use of spatial relations in referring expressions In Proceedings of the 5th International Conference on Natural Language Generation, Salt Fork OH, USA. [ pdf | slides ]

You are welcome to download the GRE3D3 corpus and use it for your own research. It would be fantastic to hear about your plans, in case you do. Just email me.