The fields of user modeling and natural language processing have been close
ly linked since the early days of user modeling. Natural language systems c
onsult user models in order to improve their understanding of users' requir
ements and to generate appropriate and relevant responses. At the same time
, the information natural language systems obtain from their users is expec
ted to increase the accuracy of their user models. In this paper, we review
natural language systems for generation, understanding and dialogue, focus
ing on the requirements and limitations these systems and user models place
on each other. We then propose avenues for future research.