Today, the Internet provides us with a vast amount of information. The amount of information and the number of users are rapidly increasing, and the use of the information is changing, as well as the number of natural languages in which people publish and communicate. This increases the difficulties when trying to harness and extract relevant and correct information.

There is a need for developing better technology that take the underlying semantics into account, as well as understand the cultural factors and the human atitudes of people with different backgrounds on the Web.

The research group on natural language technologies works with natural language processing and information access, as well with evaluation of natural language processing systems and tools.

We have in particular worked with Portuguese language technology through leading the Linguateca project.

We are also integrated in other activities in the wider department, especially in what concerns activities in semantic technologies:

•  we do research on the semantic Web in general (specifically in the geographical domain)
• on the integration of natural language with service composition in particular.