Paper: CNTS: Memory-Based Learning of Generating Repeated References

ACL ID W08-1129
Title CNTS: Memory-Based Learning of Generating Repeated References
Venue International Conference on Natural Language Generation
Session Main Conference
Year 2008
Authors

In this paper we describe our machine learning approach to the generation of referring expres- sions. As our algorithm we use memory-based learning. Our results show that in case of pre- dicting the TYPE of the expression, having one general classifier gives the best results. On the contrary, when predicting the full set of prop- erties of an expression, a combined set of spe- cialized classifiers for each subdomain gives the best performance.